© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17453
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format (month/day/year)

    oai_token-act-pair · gpt-3.5-turbo

    numeric date and time formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.81
     nomine
    -0.72
     mustard
    -0.70
     arrog
    -0.68
     chants
    -0.67
     pitched
    -0.67
     looph
    -0.66
     gorilla
    -0.66
     builder
    -0.64
    ortunately
    -0.64
    POSITIVE LOGITS
    31
    1.42
    29
    1.42
    28
    1.41
    27
    1.40
    26
    1.38
    30
    1.36
    22
    1.35
    25
    1.35
    23
    1.35
    9
    1.33
    Activations Density 0.030%

    No Known Activations