© 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. 23996
    Prev
    Next
    INDEX
    Explanations

    words related to political or theoretical concepts

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to various forms of "national" and "international" 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
    Mini
    -0.70
    Bay
    -0.69
     Flo
    -0.67
    ãģ®éŃĶ
    -0.67
    Oak
    -0.66
     Rabbit
    -0.65
    mail
    -0.64
    Bone
    -0.64
     Nap
    -0.64
     DAC
    -0.63
    POSITIVE LOGITS
    ational
    1.46
    ally
    1.09
    ationally
    1.00
    ities
    1.00
    itionally
    0.93
    ity
    0.88
    ists
    0.88
     minded
    0.85
    istries
    0.85
    emic
    0.84
    Activations Density 0.012%

    No Known Activations