© 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. 2-RES-JB
    11. 13411
    Prev
    Next
    INDEX
    Explanations

    text formatting elements, potentially related to coding or data handling

    oai_token-act-pair · gpt-3.5-turbo

    questions or phrases that express doubt or skepticism about experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]."
    -0.47
    )."
    -0.43
    ).[
    -0.43
    ''.
    -0.42
    .''
    -0.41
    ."[
    -0.41
    ".[
    -0.41
    }}
    -0.39
     theirs
    -0.39
    .""
    -0.38
    POSITIVE LOGITS
    itialized
    0.35
    outine
    0.30
     Starr
    0.30
    undrum
    0.29
    estern
    0.28
     Karin
    0.28
    gor
    0.28
    ETHOD
    0.28
    irection
    0.27
    onge
    0.27
    Activations Density 11.531%

    No Known Activations