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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 17548
    Prev
    Next
    INDEX
    Explanations

    words related to possessions or belonging to someone

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms related to people and their concerns

    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
    rette
    -0.88
    ansas
    -0.80
    inet
    -0.77
    vell
    -0.77
    lling
    -0.74
    lin
    -0.73
    lehem
    -0.72
    obin
    -0.71
    APTER
    -0.71
    ffen
    -0.71
    POSITIVE LOGITS
     minds
    0.98
     noses
    0.97
     own
    0.95
     favourite
    0.92
     intentions
    0.91
     opinions
    0.90
     asses
    0.90
     frustrations
    0.89
     favorite
    0.89
     efforts
    0.89
    Activations Density 0.124%

    No Known Activations