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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 523
    Prev
    Next
    INDEX
    Explanations

    words related to achieving goals or objectives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "achieve" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cloth
    -0.73
    seed
    -0.66
    ourcing
    -0.63
    ping
    -0.62
    jud
    -0.61
     chrom
    -0.61
    ©¶æ
    -0.60
    dr
    -0.60
    osate
    -0.59
    phe
    -0.58
    POSITIVE LOGITS
     attainment
    0.86
    ments
    0.82
     accomplish
    0.81
    iage
    0.80
     achieve
    0.78
     greatness
    0.78
     mastery
    0.77
    chieve
    0.77
     fruition
    0.77
     accomplishment
    0.75
    Activations Density 0.032%

    No Known Activations