© 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. 9-RES-JB
    11. 14351
    Prev
    Next
    INDEX
    Explanations

    information about various factors and their impact on different situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various factors influencing a situation or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osures
    -0.76
    phabet
    -0.75
     offerings
    -0.73
    efer
    -0.73
    iens
    -0.72
    enda
    -0.71
    aris
    -0.70
    OWS
    -0.68
     pilgr
    -0.67
     Begin
    -0.65
    POSITIVE LOGITS
     factors
    1.43
     factor
    1.36
     caus
    1.24
     contribut
    1.22
     causation
    1.21
     confounding
    1.20
     contributing
    1.18
     correlated
    1.18
     affecting
    1.17
    factor
    1.16
    Activations Density 0.844%

    No Known Activations