© 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. 20308
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns followed by a numeric identifier

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to 'these' and 'those' as indicators of exemplification or emphasis in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Adds
    -0.75
    ossibility
    -0.69
    iosis
    -0.69
    culosis
    -0.69
    unk
    -0.67
    Comment
    -0.66
    Pub
    -0.65
    igation
    -0.65
    mma
    -0.65
    herence
    -0.64
    POSITIVE LOGITS
     guys
    1.31
     kinds
    1.24
     sorts
    1.13
     days
    1.09
     dudes
    1.02
     types
    1.00
     fellows
    0.97
     things
    0.96
     idiots
    0.96
     folks
    0.96
    Activations Density 0.105%

    No Known Activations