INDEX

Explanations

phrases related to movement or change in position

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "slip" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

types

-0.79

ships

-0.78

source

-0.68

original

-0.68

models

-0.67

zo

-0.66

à¼

-0.66

izes

-0.66

rior

-0.65

lat

-0.65

POSITIVE LOGITS

 slipped

0.88

weed

0.88

BuyableInstoreAndOnline

0.86

 slipping

0.84

avorite

0.81

nesday

0.80

 undone

0.75

 crept

0.74

avier

0.74

ecided

0.70

Activations Density 0.010%

phrases related to movement or change in position

occurrences of the word "slip" and its variations

No Comments

No Known Activations