© 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. 7085
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "LESS" emphasized

    oai_token-act-pair · gpt-3.5-turbo

    the term "ess" and its variations in different contexts

    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
    Äį
    -0.90
    ãĥ£
    -0.73
     vitro
    -0.72
    ãĤ§
    -0.70
    bed
    -0.68
    road
    -0.68
    cells
    -0.66
    Äĩ
    -0.66
     cease
    -0.66
    stal
    -0.64
    POSITIVE LOGITS
    enger
    1.15
    entials
    0.89
    ional
    0.89
    IVE
    0.88
    iencies
    0.87
    entially
    0.83
    engers
    0.82
    essor
    0.82
    istance
    0.79
    ILA
    0.79
    Activations Density 0.010%

    No Known Activations