© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2780
    Prev
    Next
    INDEX
    Explanations

    instances of the word "evidence of"

    oai_token-act-pair · gpt-3.5-turbo

    references to evidence or proof linked to claims or situations

    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
     ILCS
    -0.83
    ahime
    -0.82
    BuyableInstoreAndOnline
    -0.77
    Vert
    -0.73
     Rout
    -0.71
    zie
    -0.71
    Home
    -0.70
    hare
    -0.69
    Bomb
    -0.67
    Hug
    -0.66
    POSITIVE LOGITS
     validity
    0.98
     dispro
    0.90
     corrobor
    0.90
     eyewitness
    0.88
     evidence
    0.82
    evidence
    0.81
     inacc
    0.81
     wrongdoing
    0.81
     causation
    0.80
     factual
    0.80
    Activations Density 0.172%

    No Known Activations