Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 22553
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs related to allowing or permitting actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of first-person and second-person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lump
    -0.69
    govtrack
    -0.65
    olate
    -0.63
    hips
    -0.63
    ĪĴ
    -0.63
    angel
    -0.62
    Sax
    -0.61
     riddled
    -0.59
    ÑĢ
    -0.57
    gall
    -0.57
    POSITIVE LOGITS
     access
    0.78
    SpaceEngineers
    0.73
     unrestricted
    0.73
     unlimited
    0.70
     peek
    0.69
     lapse
    0.68
     freely
    0.67
     deduction
    0.66
     flexibility
    0.65
     sake
    0.65
    Activations Density 0.192%

    No Known Activations