© 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. 7-RES-JB
    11. 2675
    Prev
    Next
    INDEX
    Explanations

    names related to "Mar" or similar prefixes like "Mar-" and "Mar" followed by a vowel

    oai_token-act-pair · gpt-3.5-turbo

    references to names, particularly people named "Mar" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    footed
    -0.68
    avorite
    -0.64
    Reviewer
    -0.64
    withstanding
    -0.64
     lawy
    -0.60
     embodiments
    -0.55
     academ
    -0.54
     thumb
    -0.54
     ancest
    -0.54
     HDD
    -0.52
    POSITIVE LOGITS
    opa
    0.72
    oes
    0.67
     Wynne
    0.66
    chal
    0.65
    borough
    0.65
    atis
    0.64
    INAL
    0.62
    idge
    0.62
    roth
    0.62
    quin
    0.62
    Activations Density 0.107%

    No Known Activations