© 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. 24009
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'tunnel'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "funnels" and related terms within a specific context

    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
    ETA
    -0.95
    Animal
    -0.88
    ISO
    -0.82
    CONCLUS
    -0.81
    Interstitial
    -0.78
    ãģ¦
    -0.76
    PUT
    -0.75
    Dur
    -0.72
    Birth
    -0.72
     STATS
    -0.72
    POSITIVE LOGITS
    nel
    1.43
    ounge
    1.01
    nels
    0.99
    theless
    0.97
    ilst
    0.96
    ulty
    0.95
    zzle
    0.95
    igible
    0.93
    asus
    0.92
    ugu
    0.92
    Activations Density 0.004%

    No Known Activations