© 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. 2-RES-JB
    6. 971
    Prev
    Next
    INDEX
    Explanations

    words related to conflict or battle

    oai_token-act-pair · gpt-3.5-turbo

    the past tense of the verb 'fight'

    oai_token-act-pair · gpt-4-turbo

    instances of the word "fought" related to conflict or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angan
    -0.82
    adan
    -0.71
    abuse
    -0.69
    armed
    -0.67
     impunity
    -0.67
    liction
    -0.65
    ateral
    -0.65
    oration
    -0.63
    itarian
    -0.62
    ablo
    -0.62
    POSITIVE LOGITS
    ĸļ
    0.88
    nesday
    0.88
    escription
    0.85
     fought
    0.81
    uled
    0.76
     unsuccessfully
    0.76
    ¯¯¯¯¯¯¯¯
    0.74
     valiant
    0.70
    reath
    0.69
    ategory
    0.69
    Activations Density 0.055%

    No Known Activations