INDEX

Explanations

instances of words related to the concept of returning or going back

oai_token-act-pair · gpt-3.5-turbo

references to returning to a previous state or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Interstitial

-0.76

urst

-0.75

ghai

-0.71

erity

-0.63

isson

-0.62

 furthermore

-0.61

ãģ¦

-0.61

 compares

-0.61

oS

-0.60

mentation

-0.59

POSITIVE LOGITS

 basics

0.96

 fray

0.93

 fold

0.91

 original

0.90

 haunt

0.83

 whence

0.82

 senses

0.81

 originals

0.78

 drawing

0.76

 groove

0.76

Activations Density 0.169%

instances of words related to the concept of returning or going back

references to returning to a previous state or condition

No Comments

No Known Activations