© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 809
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific condition or consequence that happens if a particular action is not taken

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "otherwise."

    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
     Secondly
    -0.65
    ng
    -0.62
     GOODMAN
    -0.60
    Secondly
    -0.59
    nesday
    -0.57
     secondly
    -0.56
    nce
    -0.56
     Percentage
    -0.56
     Extension
    -0.55
     canvas
    -0.55
    POSITIVE LOGITS
    worldly
    0.83
    SPONSORED
    0.82
     inexplicable
    0.81
     unheard
    0.78
     unrem
    0.78
     indistinguishable
    0.77
     unemploy
    0.77
     guiActiveUnfocused
    0.77
     unknown
    0.75
     known
    0.74
    Activations Density 0.026%

    No Known Activations