© 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. 8-RES-JB
    11. 20061
    Prev
    Next
    INDEX
    Explanations

    numbers related to measurements or dimensions

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to measurements or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uler
    -0.76
    BOOK
    -0.68
    urer
    -0.68
    achus
    -0.64
    hold
    -0.64
    ifice
    -0.64
    igent
    -0.64
    yang
    -0.63
    hend
    -0.63
    ezvous
    -0.62
    POSITIVE LOGITS
     ILCS
    1.27
    «ĺ
    0.94
    mph
    0.83
    00
    0.81
    CTV
    0.81
     mph
    0.79
    MHz
    0.76
    %);
    0.76
    Hz
    0.75
    GMT
    0.74
    Activations Density 0.080%

    No Known Activations