© 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. 11-RES-JB
    11. 10732
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future actions or ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.70
    #$#$
    -0.67
    jection
    -0.64
    ollow
    -0.63
    ð
    -0.61
    tsky
    -0.61
    OTOS
    -0.60
    ĸļ
    -0.58
     differs
    -0.57
     interven
    -0.54
    POSITIVE LOGITS
     gonna
    2.17
     going
    2.07
    going
    1.57
     Going
    1.24
     destined
    1.18
     likely
    1.17
     chance
    1.05
     supposed
    1.03
     slated
    1.01
    Going
    0.99
    Activations Density 0.412%

    No Known Activations