© 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. 9889
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting information or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reported information or statements from sources

    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
    izont
    -0.89
    ãĥİ
    -0.82
    wow
    -0.81
    ĸļ
    -0.80
    wcsstore
    -0.80
    aho
    -0.79
    always
    -0.79
    ãĥĩ
    -0.79
    ãĥĺ
    -0.78
    à¦
    -0.77
    POSITIVE LOGITS
     representatives
    0.85
     officials
    0.85
     billionaire
    0.84
     unnamed
    0.82
     disgruntled
    0.81
     staffers
    0.80
     executives
    0.80
     prosecutors
    0.78
     several
    0.77
     Lt
    0.77
    Activations Density 0.230%

    No Known Activations