© 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. 14139
    Prev
    Next
    INDEX
    Explanations

    phrases surrounding the concept of time

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "it" in various contexts

    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
    scribe
    -0.72
    telling
    -0.72
    cknow
    -0.67
    quartered
    -0.65
    ãĤ¹ãĥĪ
    -0.64
    dding
    -0.60
    holding
    -0.59
    mans
    -0.58
    ãĥı
    -0.56
    Limit
    -0.55
    POSITIVE LOGITS
     rains
    1.29
     expires
    1.24
     happens
    1.20
     happened
    1.19
     transpired
    1.16
     occurred
    1.16
     occurs
    1.13
     becomes
    1.13
    chy
    1.08
     became
    1.07
    Activations Density 0.094%

    No Known Activations