© 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. 4-RES-JB
    11. 2736
    Prev
    Next
    INDEX
    Explanations

    the word 'or' followed by a numerical activation value indicating relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    options or alternatives in various contexts

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

    No Comments

    Negative Logits
    Ĥİ
    -0.75
    Mech
    -0.66
    aturday
    -0.66
    ENE
    -0.66
    ARA
    -0.64
    aware
    -0.64
    aku
    -0.63
    uesday
    -0.63
    Ĥª
    -0.63
    ailed
    -0.61
    POSITIVE LOGITS
    acles
    1.20
    acle
    1.16
    chard
    1.13
     else
    1.06
     otherwise
    1.06
    nam
    1.02
    Else
    1.01
     alternatively
    1.00
    chid
    0.98
    acular
    0.94
    Activations Density 0.099%

    No Known Activations