INDEX

Explanations

mentions of hyperbolic or exaggerated language and descriptions

oai_token-act-pair · gpt-3.5-turbo

prefixes and suffixes related to hyperactivity or excessive states

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

baum

-0.70

pherd

-0.66

ADRA

-0.65

ometimes

-0.61

Dialogue

-0.61

ABE

-0.60

hement

-0.59

emouth

-0.58

ulhu

-0.57

 Folder

-0.57

POSITIVE LOGITS

ulic

0.92

opter

0.86

emic

0.85

olic

0.78

agog

0.76

ilic

0.74

ersive

0.72

uating

0.71

inem

0.70

olester

0.68

Activations Density 0.136%

mentions of hyperbolic or exaggerated language and descriptions

prefixes and suffixes related to hyperactivity or excessive states

No Comments

No Known Activations