© 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. 1-RES-JB
    11. 20718
    Prev
    Next
    INDEX
    Explanations

    words related to physical conditions, particularly those related to movement and actions

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that relate to struggles or challenges faced by individuals and families

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAYS
    -0.44
    RESULTS
    -0.41
    NetMessage
    -0.38
    pmwiki
    -0.35
     PLAN
    -0.33
     DATA
    -0.32
    ongyang
    -0.32
    WHERE
    -0.31
    /+
    -0.31
     CODE
    -0.31
    POSITIVE LOGITS
    abus
    0.44
    uously
    0.43
    iour
    0.40
    gins
    0.40
    abling
    0.40
    etti
    0.39
    ãĤ©
    0.39
    uin
    0.39
    uity
    0.38
    vest
    0.38
    Activations Density 2.453%

    No Known Activations