© 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. 10-RES-JB
    11. 12799
    Prev
    Next
    INDEX
    Explanations

    mentions of personal identities and expressions of disagreement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ABE
    -0.75
     fodder
    -0.70
     PBS
    -0.69
     democracy
    -0.65
     Skydragon
    -0.65
     ballots
    -0.64
     tiers
    -0.63
     ROS
    -0.62
     democracies
    -0.62
     hydrogen
    -0.61
    POSITIVE LOGITS
    m
    1.26
    mean
    1.20
    t
    1.16
    want
    1.12
    mad
    1.11
    ll
    1.09
    ma
    1.08
    never
    1.06
    felt
    1.06
    say
    1.05
    Activations Density 0.079%

    No Known Activations