© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 12848
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving success or obtaining something desirable

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "secure" and its variations in the context of acquiring support or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psc
    -0.85
    embed
    -0.74
    sin
    -0.73
    die
    -0.72
    si
    -0.69
    bow
    -0.68
    iquette
    -0.67
    rug
    -0.66
    spin
    -0.65
    example
    -0.65
    POSITIVE LOGITS
     victory
    0.91
     assurances
    0.89
     victories
    0.88
     footing
    0.87
     approval
    0.86
     approvals
    0.86
     ratification
    0.86
     passage
    0.81
     confirmation
    0.81
     concessions
    0.81
    Activations Density 0.078%

    No Known Activations