© 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. 4-RES-JB
    11. 15317
    Prev
    Next
    INDEX
    Explanations

    terms related to specific processes or actions, particularly those involving various industries or education

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to development and investment issues

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

    No Comments

    Negative Logits
    cknowled
    -0.58
     ellipt
    -0.54
    oret
    -0.52
     Mathemat
    -0.49
     Laurel
    -0.49
     fold
    -0.44
     Universe
    -0.44
     summed
    -0.43
     crow
    -0.43
     minced
    -0.43
    POSITIVE LOGITS
    smanship
    0.69
    eering
    0.65
    anship
    0.64
    .–
    0.60
     therapy
    0.59
    fare
    0.59
    dates
    0.59
    locks
    0.59
    eers
    0.58
     syndrome
    0.57
    Activations Density 0.875%

    No Known Activations