INDEX

Explanations

phrases related to events or occasions

oai_token-act-pair · gpt-3.5-turbo

words related to various forms of evaluation or assessment

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

giving

-0.72

FTWARE

-0.69

flame

-0.65

ãĤ©

-0.65

dfx

-0.64

Dim

-0.63

earchers

-0.63

ness

-0.63

Haw

-0.62

Scroll

-0.62

POSITIVE LOGITS

SHIP

0.76

chnology

0.76

htaking

0.75

rome

0.74

urally

0.72

onite

0.71

aukee

0.69

xon

0.67

rex

0.67

illac

0.66

Activations Density 0.051%

phrases related to events or occasions

words related to various forms of evaluation or assessment

No Comments

No Known Activations