INDEX

Explanations

instances of the word "List"

oai_token-act-pair · gpt-3.5-turbo

occurrences of variations of the word "List."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icago

-0.72

asio

-0.62

perty

-0.61

zza

-0.61

irgin

-0.61

 Wildcats

-0.59

GGGGGGGG

-0.58

wav

-0.57

rir

-0.56

zech

-0.56

POSITIVE LOGITS

ening

1.31

ener

1.17

eners

1.12

erv

0.95

ings

0.92

ened

0.90

ing

0.89

enable

0.89

ensen

0.87

ens

0.86

Activations Density 0.039%

instances of the word "List"

occurrences of variations of the word "List."

No Comments

No Known Activations