Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18706
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer hardware and software maintenance

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the second person possessive pronoun "your," indicating an emphasis on personal experience or possession

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

    No Comments

    Negative Logits
    ilts
    -0.81
    trak
    -0.74
     Uriel
    -0.74
    apo
    -0.73
    vous
    -0.72
     Originally
    -0.72
    wik
    -0.69
    raq
    -0.69
     Goes
    -0.69
     Detected
    -0.67
    POSITIVE LOGITS
     own
    1.61
     favourite
    1.07
     favorite
    1.06
     opponent
    1.05
    ocard
    1.05
     adversary
    1.03
     surroundings
    0.96
     imagination
    0.95
     desired
    0.94
    selves
    0.93
    Activations Density 0.120%

    No Known Activations