© 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. 6-RES-JB
    6. 24569
    Prev
    Next
    INDEX
    Explanations

    quotation marks used for direct speech

    oai_token-act-pair · gpt-3.5-turbo

    quotations or dialogue in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distribut
    -0.83
     cannabin
    -0.79
     deterrent
    -0.76
    avorite
    -0.75
    ¥ŀ
    -0.69
     princip
    -0.69
     sshd
    -0.67
     conve
    -0.67
     mainland
    -0.66
     Aval
    -0.65
    POSITIVE LOGITS
    Hey
    1.19
    Oh
    1.16
    hey
    1.07
    I
    1.04
    trust
    0.99
    tis
    0.98
    cause
    0.98
    Yo
    0.98
    Sir
    0.97
    You
    0.97
    Activations Density 0.060%

    No Known Activations