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. 1-RES-JB
    6. 14441
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "breadth" or a wide range of content or support

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concepts of breadth and treasure troves of information

    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
    aneous
    -0.86
    iated
    -0.71
     announcer
    -0.70
     announ
    -0.69
    ions
    -0.68
     tyr
    -0.68
    iants
    -0.65
     millisec
    -0.65
    iating
    -0.63
     Malf
    -0.63
    POSITIVE LOGITS
     GOODMAN
    1.05
    emouth
    0.86
    ostic
    0.82
    ographies
    0.80
    algia
    0.78
     Hopkins
    0.75
     Parables
    0.74
    urst
    0.73
    asket
    0.70
    ocent
    0.69
    Activations Density 0.034%

    No Known Activations