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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22578
    Prev
    Next
    INDEX
    Explanations

    names of universities related to Cambridge

    oai_token-act-pair · gpt-3.5-turbo

    references to the university Cambridge and classical music

    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
    swick
    -0.91
    alties
    -0.89
    ality
    -0.85
    zing
    -0.83
    unal
    -0.83
    eering
    -0.81
    bably
    -0.81
    stice
    -0.81
    zan
    -0.80
    gie
    -0.76
    POSITIVE LOGITS
     Analy
    0.84
     Blackwell
    0.66
     Anarchy
    0.65
     Integration
    0.64
    Software
    0.63
    hern
    0.60
    utils
    0.59
     tutor
    0.58
     chloride
    0.58
    rete
    0.58
    Activations Density 0.086%

    No Known Activations