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. 1-RES-JB
    6. 15386
    Prev
    Next
    INDEX
    Explanations

    text related to signing up for newsletters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Sign" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nerv
    -0.72
    ĸļ
    -0.69
    ooked
    -0.67
    70710
    -0.63
    UTE
    -0.63
    »Ĵ
    -0.62
    nesia
    -0.61
     earth
    -0.61
    UNCH
    -0.60
     Pwr
    -0.60
    POSITIVE LOGITS
    Sign
    1.36
    atories
    1.27
    sign
    1.25
    ificant
    1.18
     Sign
    1.17
    ificantly
    1.07
    atures
    0.98
     sign
    0.98
    atory
    0.97
    posts
    0.95
    Activations Density 0.007%

    No Known Activations