© 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. 9-RES-JB
    11. 18503
    Prev
    Next
    INDEX
    Explanations

    phrases related to durations or lengths of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe lengthy, challenging, or significant processes and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apon
    -0.83
    apons
    -0.80
    MpServer
    -0.71
    andise
    -0.68
    selves
    -0.68
    Self
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
    MSN
    -0.65
    SpaceEngineers
    -0.65
    Enh
    -0.65
    POSITIVE LOGITS
     ardu
    1.01
     longest
    0.91
    oried
    0.90
     slee
    0.90
     lasting
    0.88
     gru
    0.87
     winding
    0.87
     subsequ
    0.86
     tedious
    0.82
    ftime
    0.80
    Activations Density 0.156%

    No Known Activations