Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 341
    Prev
    Next
    INDEX
    Explanations

    words related to legal activities and people involved in legal matters

    oai_token-act-pair · gpt-3.5-turbo

    words associated with solicitation and demands

    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
     millenn
    -0.75
     corrid
    -0.70
     slick
    -0.70
     subscript
    -0.69
     manageable
    -0.67
     steep
    -0.67
    ©¶æ
    -0.66
     myster
    -0.64
     forgiving
    -0.63
     defensively
    -0.63
    POSITIVE LOGITS
    ead
    0.87
    opoulos
    0.86
    sky
    0.81
    ertain
    0.80
    eus
    0.80
    icz
    0.79
    ovic
    0.79
    rad
    0.79
    ove
    0.78
    ais
    0.77
    Activations Density 0.314%

    No Known Activations