INDEX

Explanations

words related to upward or downward trends

oai_token-act-pair · gpt-3.5-turbo

terms related to upward and downward trends or movements

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

abase

-0.74

mong

-0.74

TOP

-0.73

 Mamm

-0.72

ghazi

-0.71

DN

-0.71

BuyableInstoreAndOnline

-0.69

rol

-0.66

ument

-0.66

tek

-0.65

POSITIVE LOGITS

¥ŀ

0.96

 trajectory

0.87

 traject

0.86

srf

0.84

wcs

0.77

 pressure

0.77

stairs

0.76

dash

0.76

grading

0.75

 revisions

0.75

Activations Density 0.028%

words related to upward or downward trends

terms related to upward and downward trends or movements

No Comments

No Known Activations