© 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. 1-RES-JB
    11. 3211
    Prev
    Next
    INDEX
    Explanations

    words related to communication and technology, such as software and program

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'l' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.87
    ħĭ
    -0.79
     prof
    -0.68
    éĹĺ
    -0.66
    ij士
    -0.65
     reused
    -0.64
     Suns
    -0.64
     unfocusedRange
    -0.62
     coll
    -0.62
     chatting
    -0.62
    POSITIVE LOGITS
    ayers
    1.24
    azy
    1.21
    enny
    1.14
    oyd
    1.13
    oom
    1.12
    ibraries
    1.08
    ibr
    1.07
    agues
    1.06
    aughlin
    1.05
    adders
    1.05
    Activations Density 0.024%

    No Known Activations