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. 7-RES-JB
    6. 1954
    Prev
    Next
    INDEX
    Explanations

    comparisons using the structure "not as ... as"

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing the word "as"

    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
    HAEL
    -0.68
    \<
    -0.67
     Unlock
    -0.67
    å§«
    -0.65
     +++
    -0.64
    ����
    -0.64
     OWN
    -0.61
     Wage
    -0.61
     Loaded
    -0.60
     COUR
    -0.59
    POSITIVE LOGITS
    imilar
    0.91
     flashy
    0.87
    yet
    0.85
    pired
    0.84
     far
    0.84
     much
    0.83
    ndra
    0.83
     glamorous
    0.80
    pires
    0.80
     noticeable
    0.78
    Activations Density 0.044%

    No Known Activations