INDEX

Explanations

dialogue related to discussions or conversations

oai_token-act-pair · gpt-3.5-turbo

dialogues and conversational interactions

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

ocations

-0.72

etheless

-0.71

é¾įå

-0.68

yet

-0.63

moil

-0.63

Fla

-0.62

imes

-0.62

 oneself

-0.62

 Previous

-0.61

ielding

-0.60

POSITIVE LOGITS

me

0.90

 whine

0.71

us

0.68

tyr

0.66

 fuckin

0.65

 bark

0.64

 remorse

0.64

istar

0.64

 nicer

0.64

 biscuits

0.62

Activations Density 0.914%

dialogue related to discussions or conversations

dialogues and conversational interactions

No Comments

No Known Activations