© 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. 0-RES-JB
    11. 3596
    Prev
    Next
    INDEX
    Explanations

    places or names containing the letters "ah"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sound 'ah' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compos
    -0.82
     components
    -0.65
     lumber
    -0.62
     reproduced
    -0.62
     Tactics
    -0.62
     extracts
    -0.59
     multiplying
    -0.59
     Vital
    -0.59
     mobility
    -0.58
     reprodu
    -0.58
    POSITIVE LOGITS
    ah
    4.10
    ahs
    3.11
    AH
    2.23
    ahah
    1.94
    aah
    1.87
    ahi
    1.68
    aha
    1.65
    ahn
    1.54
    oh
    1.53
    nah
    1.53
    Activations Density 0.024%

    No Known Activations