© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3633
    Prev
    Next
    INDEX
    Explanations

    phrases related to goals and intentions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statements related to objectives or aims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culus
    -0.54
     blat
    -0.53
    gettable
    -0.53
     Slip
    -0.52
     Celtic
    -0.51
     SOFTWARE
    -0.51
     Celt
    -0.50
     Pyr
    -0.50
     Virus
    -0.50
    BuyableInstoreAndOnline
    -0.49
    POSITIVE LOGITS
     is
    0.96
     was
    0.91
     remains
    0.83
     revolves
    0.82
     consists
    0.76
     boils
    0.76
    posts
    0.73
     seems
    0.73
     isn
    0.72
     wasn
    0.72
    Activations Density 0.197%

    No Known Activations