INDEX

Explanations

references to things being large or enlarged

oai_token-act-pair · gpt-3.5-turbo

words related to size, specifically those indicating something large or an increase in size

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iggins

-0.77

onder

-0.73

oti

-0.70

iosyncr

-0.70

onna

-0.69

okin

-0.66

gnu

-0.63

senal

-0.63

onto

-0.63

etheless

-0.62

POSITIVE LOGITS

large

0.90

 sized

0.82

larg

0.77

 intestine

0.75

 Telescope

0.74

vier

0.72

achusetts

0.72

 enlarg

0.72

ature

0.71

 sizes

0.71

Activations Density 0.014%

references to things being large or enlarged

words related to size, specifically those indicating something large or an increase in size

No Comments

No Known Activations