© 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. 24201
    Prev
    Next
    INDEX
    Explanations

    terms related to rotations or sequences within a set context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rotation" in various contexts

    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
    stract
    -0.74
    asper
    -0.74
     Marina
    -0.68
    Obama
    -0.67
    erry
    -0.67
    tein
    -0.67
    CHA
    -0.67
    atered
    -0.66
    ramid
    -0.63
    Priv
    -0.62
    POSITIVE LOGITS
     rotation
    1.49
     rotate
    0.95
     destro
    0.90
     rotated
    0.84
     purge
    0.83
     tremend
    0.81
     rotating
    0.80
     proble
    0.80
     rot
    0.79
    otation
    0.79
    Activations Density 0.007%

    No Known Activations