© 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. 1-RES-JB
    11. 20087
    Prev
    Next
    INDEX
    Explanations

    rock-related terms and references

    oai_token-act-pair · gpt-3.5-turbo

    references to rock music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntil
    -0.75
    URES
    -0.72
    9999
    -0.69
    perial
    -0.69
    oral
    -0.69
    ffect
    -0.67
    rha
    -0.67
    urses
    -0.66
    odore
    -0.65
    REM
    -0.65
    POSITIVE LOGITS
     rock
    1.15
    castle
    0.94
    rock
    0.89
    lake
    0.89
    ppelin
    0.87
     rocks
    0.85
     climbers
    0.85
     climbs
    0.84
     formations
    0.83
     climbing
    0.81
    Activations Density 0.009%

    No Known Activations