© 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. 21489
    Prev
    Next
    INDEX
    Explanations

    numbers in a specific format, likely part of a technical code or system

    oai_token-act-pair · gpt-3.5-turbo

    topics related to significant social or political issues

    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
     ageing
    -1.18
     manoeuv
    -1.09
     humour
    -1.05
     civilisation
    -1.01
     favourite
    -0.98
     organis
    -0.96
     travellers
    -0.95
     neighbour
    -0.93
     maths
    -0.92
     neighbours
    -0.92
    POSITIVE LOGITS
    Advertisement
    0.99
    SPONSORED
    0.97
    advertisement
    0.95
    NPR
    0.89
    —"
    0.86
    ³³³³³³³³
    0.84
    ³³³³
    0.83
    Correction
    0.82
    ³³³³³³³³³³³³³³³³
    0.81
    Additionally
    0.79
    Activations Density 0.383%

    No Known Activations