© 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. 0-RES-JB
    11. 4128
    Prev
    Next
    INDEX
    Explanations

    texts related to the city of Houston

    oai_token-act-pair · gpt-3.5-turbo

    variations of the term "Houlton."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dated
    -0.63
     frame
    -0.62
     insecure
    -0.61
     framing
    -0.60
     Disp
    -0.60
     Indo
    -0.59
     registry
    -0.59
     mounting
    -0.59
     fund
    -0.59
     JD
    -0.59
    POSITIVE LOGITS
    oul
    4.47
    ouls
    2.83
    oult
    1.56
    ou
    1.53
    oulos
    1.48
    OU
    1.20
    oud
    1.18
    oun
    1.17
    ouf
    1.13
    ouk
    1.05
    Activations Density 0.015%

    No Known Activations