INDEX

Explanations

words related to intensity, emotion, or importance

oai_token-act-pair · gpt-3.5-turbo

occurrences of the prefix "ind-" 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 @ 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

Ĥİ

-0.86

veyard

-0.76

sonian

-0.73

 litter

-0.70

 Fenrir

-0.66

calling

-0.66

berman

-0.63

bilt

-0.62

 tanks

-0.61

zzo

-0.61

POSITIVE LOGITS

etermin

1.19

ented

1.18

ivid

1.10

irection

1.08

ents

1.06

irect

1.00

ignant

0.98

oled

0.95

ependence

0.94

istant

0.94

Activations Density 0.015%

words related to intensity, emotion, or importance

occurrences of the prefix "ind-" in various contexts

No Comments

No Known Activations