© 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. 9986
    Prev
    Next
    INDEX
    Explanations

    references to a specific gaming community or company

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific gaming community or brand

    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
     consec
    -0.74
     revolving
    -0.67
     FISA
    -0.65
     compounded
    -0.65
     politic
    -0.61
     deposition
    -0.60
     seat
    -0.59
     misleading
    -0.59
     filings
    -0.59
     chemotherapy
    -0.59
    POSITIVE LOGITS
    blers
    1.45
    etime
    1.29
    bit
    1.28
    estate
    1.24
    bitious
    1.23
    eworks
    1.18
    estone
    1.15
    emaker
    1.10
    eworld
    1.10
    azing
    1.09
    Activations Density 0.018%

    No Known Activations