© 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. 7-RES-JB
    11. 21416
    Prev
    Next
    INDEX
    Explanations

    references to pairs of objects or items

    oai_token-act-pair · gpt-3.5-turbo

    references to items in pairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.81
    inez
    -0.73
     Occupations
    -0.71
    sbm
    -0.69
    INA
    -0.68
    ADRA
    -0.68
    ESCO
    -0.67
    emetery
    -0.65
    schild
    -0.64
    ablishment
    -0.64
    POSITIVE LOGITS
    ings
    1.00
    pair
    0.89
    wise
    0.88
    rings
    0.88
     mates
    0.81
    ably
    0.80
    horn
    0.76
    ring
    0.73
     paired
    0.73
     mate
    0.73
    Activations Density 0.028%

    No Known Activations