© 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. 0-RES-JB
    11. 22732
    Prev
    Next
    INDEX
    Explanations

    terms related to increasing or raising something, particularly prices or levels

    oai_token-act-pair · gpt-3.5-turbo

    references to increases in measurements or fees, particularly related to hikes or climbs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocent
    -0.73
     Innocent
    -0.71
    otent
    -0.69
    iov
    -0.68
     mould
    -0.67
    oman
    -0.65
    nan
    -0.63
    cell
    -0.63
    ato
    -0.63
    ency
    -0.63
    POSITIVE LOGITS
     hike
    3.66
     hikes
    3.20
     hiking
    3.03
     hikers
    2.22
     trek
    1.59
    iked
    1.33
     jog
    1.26
     climb
    1.25
     skiing
    1.24
     trail
    1.22
    Activations Density 0.020%

    No Known Activations