© 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. 11198
    Prev
    Next
    INDEX
    Explanations

    the word "Except" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "except" and its variations, indicating a focus on exceptions or contrasts

    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
    taboola
    -0.61
    è¦ļéĨĴ
    -0.61
     survey
    -0.60
    "}],"
    -0.59
    idated
    -0.58
    VA
    -0.57
     swarm
    -0.57
     collected
    -0.56
     extracted
    -0.55
     sym
    -0.55
    POSITIVE LOGITS
    ional
    1.12
    Except
    1.03
     Except
    0.98
    soever
    0.97
    withstanding
    0.87
    ishly
    0.82
    erred
    0.82
    except
    0.81
    lihood
    0.81
    hesda
    0.81
    Activations Density 0.004%

    No Known Activations