© 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. 20458
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistics and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical prescriptions and legal offenses

    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
    ospels
    -0.74
    aughs
    -0.67
    ertain
    -0.65
    xon
    -0.61
    lihood
    -0.59
    wealth
    -0.56
    abilia
    -0.55
    aud
    -0.54
    Thumbnail
    -0.54
     Fame
    -0.52
    POSITIVE LOGITS
     altogether
    0.82
     pertaining
    0.81
     originating
    0.81
     totaling
    0.78
     elsewhere
    0.77
     ranging
    0.76
     involving
    0.75
     consisting
    0.73
     comparable
    0.72
     relating
    0.72
    Activations Density 0.590%

    No Known Activations