INDEX

Explanations

names (especially 'Lloyd') and possibly locations or events related to those names

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lloyd" and related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

cess

-0.91

bell

-0.89

shire

-0.88

stall

-0.82

brid

-0.80

fold

-0.78

bred

-0.76

cn

-0.75

Interstitial

-0.74

vision

-0.73

POSITIVE LOGITS

yip

0.77

ittal

0.73

ecause

0.71

afort

0.69

 Ridley

0.68

appy

0.68

 membranes

0.66

ermott

0.66

halla

0.65

eki

0.65

Activations Density 0.157%

names (especially 'Lloyd') and possibly locations or events related to those names

mentions of the name "Lloyd" and related entities

No Comments

No Known Activations