© 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. 2-RES-JB
    11. 24036
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'bitter'

    oai_token-act-pair · gpt-3.5-turbo

    words ending in 'itter'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cephal
    -0.72
     Kingdoms
    -0.63
    lez
    -0.63
     distinguishing
    -0.61
    ilitation
    -0.60
    Ro
    -0.60
     arresting
    -0.60
    Ward
    -0.59
    pages
    -0.58
     fictional
    -0.58
    POSITIVE LOGITS
    cair
    0.91
    geist
    0.88
    itter
    0.85
    igible
    0.83
    ing
    0.76
    meier
    0.75
    bug
    0.75
    ngth
    0.75
     extraord
    0.74
    idge
    0.73
    Activations Density 0.006%

    No Known Activations