© 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. 23205
    Prev
    Next
    INDEX
    Explanations

    phrases indicating unexpected or surprising outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase structure "only to" followed by various actions or outcomes

    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
    ahead
    -0.82
    ahime
    -0.72
    mining
    -0.71
    ocative
    -0.67
    aim
    -0.67
    kernel
    -0.66
    calling
    -0.65
    umption
    -0.65
    medium
    -0.65
    blood
    -0.64
    POSITIVE LOGITS
     realise
    1.30
     discover
    1.30
     realize
    1.23
     succumb
    1.13
     reapp
    1.12
     find
    1.10
     stumble
    1.08
     lose
    1.04
     disappear
    1.01
     vanish
    1.01
    Activations Density 0.049%

    No Known Activations