© 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. 8502
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial and economic terms, such as "short-circuit," "short of," and "short-term."

    oai_token-act-pair · gpt-3.5-turbo

    references to short-term limitations or conditions

    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
     Cosponsors
    -0.83
     è£ıç
    -0.76
     sqor
    -0.67
     Mens
    -0.67
    =-=-=-=-
    -0.66
     UD
    -0.66
     Dign
    -0.65
     Accountability
    -0.63
     kindred
    -0.63
     Meridian
    -0.63
    POSITIVE LOGITS
    sighted
    0.78
     (<
    0.78
    Js
    0.74
    hand
    0.72
    yip
    0.71
    notice
    0.69
    circ
    0.67
    cise
    0.67
    lock
    0.66
    handed
    0.65
    Activations Density 0.106%

    No Known Activations