© 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. 24105
    Prev
    Next
    INDEX
    Explanations

    words related to innovation and transformation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to innovation and persuasion

    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
    ãĤº
    -0.79
     Coverage
    -0.68
     Amendments
    -0.66
    CN
    -0.66
    mpeg
    -0.63
    473
    -0.63
     Supplemental
    -0.62
     FACE
    -0.61
     Amendment
    -0.61
     Inspection
    -0.61
    POSITIVE LOGITS
     woo
    1.04
    ed
    0.96
    educated
    0.90
     reinvent
    0.89
    edIn
    0.83
    clus
    0.80
    issance
    0.79
    ovember
    0.78
    eer
    0.78
    estern
    0.77
    Activations Density 0.025%

    No Known Activations