© 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. 8-RES-JB
    11. 22491
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to depth or intensity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey depth or intensity of emotion or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppable
    -0.77
    orious
    -0.71
    icans
    -0.69
    ULE
    -0.67
    roma
    -0.66
    annon
    -0.66
    uthor
    -0.66
    Ĥİ
    -0.65
    EED
    -0.65
    Frames
    -0.64
    POSITIVE LOGITS
     vein
    1.05
    ened
    1.01
     pockets
    0.95
     seeded
    0.92
     penetration
    0.88
     breaths
    0.87
    ening
    0.85
     dive
    0.84
     rooted
    0.82
     deep
    0.81
    Activations Density 0.027%

    No Known Activations