© 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. 2-RES-JB
    11. 9333
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the phrase "when it comes to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Background
    -0.51
     FANTASY
    -0.46
     Archer
    -0.44
     Pastebin
    -0.43
     âĶľâĶĢâĶĢ
    -0.41
     Thank
    -0.40
    cknowled
    -0.40
     Begin
    -0.40
    ++++++++++++++++
    -0.40
     Transparency
    -0.39
    POSITIVE LOGITS
    nt
    0.50
     menstru
    0.44
    =]
    0.43
    ocument
    0.42
    itant
    0.42
    iggurat
    0.42
    igi
    0.41
    okane
    0.41
     interrupted
    0.41
    itate
    0.41
    Activations Density 1.839%

    No Known Activations