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. 8805
    Prev
    Next
    INDEX
    Explanations

    references to new institutions or systems being established

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of new developments, actions, or initiatives in a structured/professional context, such as new centers, methods, systems, guidelines, or evidence

    oai_token-act-pair · gpt-3.5-turbo
    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
    otal
    -0.88
    anuts
    -0.83
    unction
    -0.68
    ubes
    -0.68
    akespeare
    -0.67
    umann
    -0.66
    abal
    -0.66
    formance
    -0.65
    emo
    -0.63
    ecause
    -0.63
    POSITIVE LOGITS
     hires
    0.84
     arrivals
    0.79
     refreshed
    0.78
     revamped
    0.76
     architectures
    0.74
    Sov
    0.74
     entrants
    0.72
     recruits
    0.71
     hire
    0.69
     redesigned
    0.66
    Activations Density 0.430%

    No Known Activations