© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12868
    Prev
    Next
    INDEX
    Explanations

    instances where something is being used for a specific purpose or intention

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the usage of something as a tool or means to achieve various ends

    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
    akings
    -0.77
     Aware
    -0.69
    LINE
    -0.67
    irez
    -0.67
     Rebell
    -0.66
    odore
    -0.65
    chev
    -0.65
    rolet
    -0.64
    Heart
    -0.64
    Benz
    -0.63
    POSITIVE LOGITS
     leverage
    1.26
     fodder
    1.06
     filler
    1.01
     bargaining
    1.00
     bait
    0.98
     ammunition
    0.96
     justification
    0.94
     inspiration
    0.93
     propell
    0.93
     shorthand
    0.92
    Activations Density 0.062%

    No Known Activations