© 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. 2-RES-JB
    11. 980
    Prev
    Next
    INDEX
    Explanations

    the word "attacks"

    oai_token-act-pair · gpt-4-turbo

    terms related to aggressive actions or threats, specifically the word "attacks"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "attacks" and its variations in the text

    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
     Combine
    -0.66
    OVA
    -0.66
    dit
    -0.65
     Vale
    -0.63
    YC
    -0.62
     Harmon
    -0.62
    theless
    -0.61
     Hemp
    -0.60
     Ment
    -0.59
     Mole
    -0.59
    POSITIVE LOGITS
     attacks
    1.08
    attack
    1.04
    attacks
    0.95
     attack
    0.93
     Attacks
    0.85
     attackers
    0.83
    Attack
    0.81
    etting
    0.79
    iveness
    0.79
    pread
    0.78
    Activations Density 0.023%

    No Known Activations