INDEX

Explanations

phrases comparing something to common objects or actions in a descriptive manner

oai_token-act-pair · gpt-3.5-turbo

similes and metaphors that involve the word "like."

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

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rity

-0.78

Events

-0.75

videos

-0.74

scl

-0.73

items

-0.73

iott

-0.72

Fit

-0.71

tm

-0.71

Interested

-0.71

abilities

-0.71

POSITIVE LOGITS

 bunch

1.05

lot

0.91

 proverbial

0.89

 sponge

0.89

 typical

0.88

 miniature

0.85

 newborn

0.84

 dozen

0.83

 glove

0.83

 multitude

0.82

Activations Density 0.122%

phrases comparing something to common objects or actions in a descriptive manner

similes and metaphors that involve the word "like."

No Comments

No Known Activations