© 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. 4128
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a transition or a shift in focus

    oai_token-act-pair · gpt-3.5-turbo

    instances where specific subjects are highlighted as significant or impactful within a context

    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
    ardless
    -0.76
    sequent
    -0.74
    rn
    -0.71
    ranean
    -0.71
    iox
    -0.69
    itary
    -0.67
    ttp
    -0.66
    same
    -0.63
     Than
    -0.63
    aren
    -0.63
    POSITIVE LOGITS
     shines
    1.21
     shine
    1.17
     excel
    1.02
     trouble
    0.92
     nutshell
    0.89
     exce
    0.81
     dilemma
    0.79
     tricky
    0.77
     kicker
    0.75
     REALLY
    0.75
    Activations Density 0.172%

    No Known Activations