© 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. 1-RES-JB
    11. 7694
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges or difficulties, particularly uphill battles and snowball effects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe struggles or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATURE
    -0.83
    AU
    -0.78
    atory
    -0.77
    ulet
    -0.74
    unal
    -0.74
    ural
    -0.73
    ule
    -0.72
    ury
    -0.68
    ancies
    -0.68
    Ring
    -0.67
    POSITIVE LOGITS
     uphill
    1.24
     downhill
    0.96
     unden
    0.89
     slope
    0.83
     adolesc
    0.83
     hill
    0.82
     slopes
    0.81
    stairs
    0.78
     stair
    0.78
     convol
    0.77
    Activations Density 0.010%

    No Known Activations