© 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. 16893
    Prev
    Next
    INDEX
    Explanations

    letters followed by numbers, potentially representing system updates or messages

    oai_token-act-pair · gpt-3.5-turbo

    references to "TER" and its variants, suggesting it is focused on specific terms or technical jargon within a particular context

    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
     Lomb
    -0.78
    cean
    -0.72
    glers
    -0.69
    ¢
    -0.66
    apache
    -0.63
    ãħĭ
    -0.63
     Singer
    -0.63
     Kenya
    -0.63
     tune
    -0.61
     Ghana
    -0.58
    POSITIVE LOGITS
    TER
    1.06
    theless
    1.03
    ROR
    0.98
    ranean
    0.95
    miah
    0.89
     confir
    0.87
    rane
    0.86
    TY
    0.86
    RY
    0.85
    LOAD
    0.84
    Activations Density 0.006%

    No Known Activations