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. 9-RES-JB
    6. 12992
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to providing support or validation

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to support or endorsement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entric
    -0.88
    itizen
    -0.74
    orp
    -0.69
    inational
    -0.68
    ities
    -0.68
    icago
    -0.68
     ILCS
    -0.66
    nesota
    -0.66
    ptives
    -0.66
    anny
    -0.65
    POSITIVE LOGITS
    track
    1.04
    ped
    0.84
     up
    0.80
    drive
    0.76
    stab
    0.76
     away
    0.76
    GROUND
    0.75
    lash
    0.73
    dash
    0.72
    tracking
    0.71
    Activations Density 0.047%

    No Known Activations