© 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. 11313
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and programming, particularly encoding standards such as UTF-8

    oai_token-act-pair · gpt-3.5-turbo

    terms related to excessive behaviors and specific ideological references

    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
    nel
    -0.85
    iating
    -0.77
    rera
    -0.76
    iations
    -0.76
     ********************************
    -0.75
    iated
    -0.75
    ription
    -0.74
    yrights
    -0.71
    uliffe
    -0.70
    ioned
    -0.70
    POSITIVE LOGITS
    ħĭ
    0.86
    ÙĴ
    0.84
    -
    0.76
     versa
    0.75
    ĻĤ
    0.74
    ãĤ·ãĥ£
    0.73
     Clicker
    0.70
    vention
    0.69
    »Ĵ
    0.67
    76561
    0.66
    Activations Density 0.040%

    No Known Activations