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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 17331
    Prev
    Next
    INDEX
    Explanations

    themes related to personal experiences and observations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal achievement or promise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.73
    yden
    -0.70
    xus
    -0.64
    coal
    -0.63
     Drivers
    -0.60
     Areas
    -0.59
    olin
    -0.59
     PsyNet
    -0.59
     Byz
    -0.58
    bis
    -0.57
    POSITIVE LOGITS
     suddenly
    0.83
     blatantly
    0.81
    respected
    0.74
    ocious
    0.74
     honestly
    0.74
     disrespect
    0.73
     such
    0.72
    epad
    0.70
     prestigious
    0.70
    ?!"
    0.70
    Activations Density 0.833%

    No Known Activations