© 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. 4-RES-JB
    11. 2960
    Prev
    Next
    INDEX
    Explanations

    the letter "Ķ"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol representation

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

    No Comments

    Negative Logits
    omnia
    -0.89
    ĸļ
    -0.87
    bourg
    -0.82
    kers
    -0.78
    */(
    -0.78
    ppelin
    -0.77
    osponsors
    -0.76
    ngth
    -0.76
    enburg
    -0.75
    itism
    -0.75
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    1.24
    âĶĢâĶĢ
    1.16
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.14
    âķIJâķIJ
    1.03
    âĶĢ
    0.86
    Ķ
    0.84
    ãĥ¥
    0.81
    »
    0.78
    TER
    0.76
    aneous
    0.74
    Activations Density 0.010%

    No Known Activations