© 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. 3-RES-JB
    11. 15232
    Prev
    Next
    INDEX
    Explanations

    locations or place names that end with "pur"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pur" and its variations, along with words associated with heat, intensity, or extreme conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izz
    -0.59
     gobl
    -0.57
     Pack
    -0.56
     seaw
    -0.56
    MP
    -0.55
     Room
    -0.54
    VM
    -0.54
     Commands
    -0.54
     Wizard
    -0.53
     Moon
    -0.53
    POSITIVE LOGITS
    theless
    1.07
    hyde
    0.99
    tenance
    0.98
    urities
    0.92
    terday
    0.91
    perature
    0.86
    cipline
    0.84
    iculty
    0.82
    acters
    0.78
    sburgh
    0.78
    Activations Density 0.052%

    No Known Activations