INDEX

Explanations

words that have a 'zo' in them, potentially looking for names or specific terms

oai_token-act-pair · gpt-3.5-turbo

the mention of the word "zo" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ivities

-0.85

lessness

-0.84

lessly

-0.79

staking

-0.77

 totality

-0.72

raising

-0.71

lain

-0.70

Interstitial

-0.69

orney

-0.67

 Norn

-0.67

POSITIVE LOGITS

zo

1.02

zzi

0.95

ombies

0.93

ombie

0.88

quin

0.86

oya

0.85

hn

0.84

eta

0.82

zz

0.76

arbon

0.76

Activations Density 0.013%

words that have a 'zo' in them, potentially looking for names or specific terms

the mention of the word "zo" and its variations in different contexts

No Comments

No Known Activations