© 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. 10-RES-JB
    11. 9916
    Prev
    Next
    INDEX
    Explanations

    statements made by authorities or officials

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported speech or statements by authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.64
     fixation
    -0.61
    76561
    -0.59
    talk
    -0.55
     Bastard
    -0.55
    ggles
    -0.52
    milo
    -0.51
     obscurity
    -0.51
    estern
    -0.50
     haun
    -0.48
    POSITIVE LOGITS
    .
    1.01
    *.
    0.83
    .–
    0.82
    .[
    0.82
    .?
    0.81
    .;
    0.79
    .*
    0.78
    .(
    0.77
    .�
    0.74
    .—
    0.72
    Activations Density 0.092%

    No Known Activations