© 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. 20419
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to prediction or assumption

    oai_token-act-pair · gpt-3.5-turbo

    terms related to predictions or assumptions about behavior or conditions

    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
    BOX
    -0.73
    Case
    -0.60
    ierrez
    -0.60
     Scotia
    -0.60
     twist
    -0.59
    Ø©
    -0.59
    hiba
    -0.59
    âĸijâĸij
    -0.58
    case
    -0.58
    OUT
    -0.57
    POSITIVE LOGITS
    efined
    1.36
    nis
    1.14
    ominated
    1.11
    essor
    1.09
    icated
    1.09
    icates
    1.07
    isp
    1.07
    etermin
    1.05
    etermination
    1.03
    awn
    1.01
    Activations Density 0.017%

    No Known Activations