© 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. 4-RES-JB
    11. 15240
    Prev
    Next
    INDEX
    Explanations

    specific programs aimed at different purposes

    oai_token-act-pair · gpt-3.5-turbo

    references to various programs, particularly those related to social services, health, or government initiatives

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

    No Comments

    Negative Logits
    Downloadha
    -0.74
     dilig
    -0.72
     CONS
    -0.70
     tremend
    -0.67
    ailable
    -0.66
    VIDEO
    -0.64
    icas
    -0.63
    å°Ĩ
    -0.63
    âĸij
    -0.62
     senses
    -0.61
    POSITIVE LOGITS
    mable
    1.33
    mers
    1.22
    matically
    1.09
    ters
    0.96
    mer
    0.94
    zee
    0.93
     Coordinator
    0.89
    mes
    0.89
    igree
    0.88
    nel
    0.87
    Activations Density 0.016%

    No Known Activations