© 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. 23410
    Prev
    Next
    INDEX
    Explanations

    names or terms related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'i' and its variations in different contexts

    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
    DERR
    -0.72
     ende
    -0.71
    OTAL
    -0.69
     Instr
    -0.66
    GGGGGGGG
    -0.63
    BILITIES
    -0.62
    thora
    -0.60
    vertisement
    -0.60
    APS
    -0.59
    JUST
    -0.59
    POSITIVE LOGITS
     hybrids
    0.96
     hybrid
    0.91
     alike
    0.81
     combo
    0.78
    ioned
    0.72
    awed
    0.67
     complexes
    0.65
    iton
    0.64
    iated
    0.64
    kered
    0.64
    Activations Density 0.303%

    No Known Activations