INDEX

Explanations

terms related to limitations or boundaries

oai_token-act-pair · gpt-3.5-turbo

references to limits and boundaries in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

issance

-0.75

lynn

-0.67

ublic

-0.67

alky

-0.66

Az

-0.66

stown

-0.65

much

-0.63

TPP

-0.63

uni

-0.62

gotten

-0.62

POSITIVE LOGITS

 imposed

1.10

 limits

0.88

 enforced

0.83

 limit

0.80

 Limits

0.80

lessly

0.80

 limitation

0.75

 allowable

0.75

 restricts

0.73

 exceeded

0.72

Activations Density 0.036%

terms related to limitations or boundaries

references to limits and boundaries in various contexts

No Comments

No Known Activations