INDEX

Explanations

references to the concept of duality, contrast, or variations within a category

oai_token-act-pair · gpt-3.5-turbo

instances of the suffix "ile" in words

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.96

olver

-0.85

iversal

-0.85

ĵĺ

-0.85

axter

-0.83

esson

-0.82

icter

-0.77

icum

-0.77

itivity

-0.76

ington

-0.76

POSITIVE LOGITS

mma

1.05

tto

1.05

zza

0.81

tta

0.77

tt

0.77

ttes

0.74

gged

0.73

vich

0.73

tsky

0.71

vel

0.68

Activations Density 0.021%

references to the concept of duality, contrast, or variations within a category

instances of the suffix "ile" in words

No Comments

No Known Activations