© 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. 6-RES-JB
    11. 14438
    Prev
    Next
    INDEX
    Explanations

    words related to strength, virility, and power

    oai_token-act-pair · gpt-3.5-turbo

    terms related to virility and virulence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.81
     captcha
    -0.80
    cedented
    -0.75
    yer
    -0.72
    IELD
    -0.71
    psey
    -0.70
    OWER
    -0.69
    uyomi
    -0.68
    req
    -0.68
     kicker
    -0.64
    POSITIVE LOGITS
    ulent
    0.99
    iously
    0.97
    gins
    0.89
    ulence
    0.86
    apore
    0.83
    git
    0.80
    atory
    0.77
    ality
    0.77
    icide
    0.76
    vi
    0.76
    Activations Density 0.043%

    No Known Activations