© 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. 8-RES-JB
    11. 6476
    Prev
    Next
    INDEX
    Explanations

    computer code syntax elements

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that represent information structure or hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.79
     Sisters
    -0.69
     shack
    -0.64
     Sco
    -0.64
     Sapphire
    -0.62
     Butt
    -0.61
    EStream
    -0.60
    theless
    -0.60
     Manhattan
    -0.60
    bda
    -0.59
    POSITIVE LOGITS
    ¬
    1.29
    į
    1.27
    º
    1.23
    Ĵ
    1.22
    ¡
    1.21
    Ķ
    1.17
    Į
    1.15
    ·
    1.14
    ¶
    1.14
    ħ
    1.14
    Activations Density 0.239%

    No Known Activations