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. 10-RES-JB
    6. 8986
    Prev
    Next
    INDEX
    Explanations

    numerical quantities associated with frequency or count

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances or occurrences of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hunt
    -0.72
    ees
    -0.70
    EA
    -0.65
    abwe
    -0.62
    amines
    -0.61
    earable
    -0.61
    ICO
    -0.60
     Released
    -0.60
    ORN
    -0.59
     pall
    -0.59
    POSITIVE LOGITS
     times
    2.16
     time
    1.71
    times
    1.63
     occasions
    1.38
    time
    1.36
     Times
    1.25
     TIM
    1.16
     Time
    1.15
    Times
    1.14
     TIME
    1.09
    Activations Density 0.414%

    No Known Activations