INDEX

Explanations

phrases indicating the benefits or qualities of something

oai_token-act-pair · gpt-3.5-turbo

the phrase "good for" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cles

-0.73

 credited

-0.72

rose

-0.66

ohn

-0.62

chenko

-0.62

stan

-0.62

Sham

-0.61

 tallied

-0.61

Mah

-0.59

 laun

-0.59

POSITIVE LOGITS

geries

1.02

 purposes

0.96

 example

0.87

agers

0.87

gery

0.86

gotten

0.85

 detecting

0.82

bidden

0.81

 awhile

0.78

ints

0.77

Activations Density 0.119%

phrases indicating the benefits or qualities of something

the phrase "good for" in various contexts

No Comments

No Known Activations