INDEX

Explanations

phrases containing definite or specific nouns and adjectives

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the" and its contextual usage

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

washing

-0.74

ibaba

-0.73

uality

-0.72

thood

-0.71

LEASE

-0.70

 absorbs

-0.69

ecast

-0.69

pection

-0.69

ances

-0.67

ADE

-0.66

POSITIVE LOGITS

 Dalai

1.30

 youngest

1.25

 eldest

1.21

 smartest

1.10

 Clintons

1.06

 aforementioned

1.06

 actress

1.03

odor

1.03

 deceased

1.03

 enigmatic

1.03

Activations Density 0.495%

phrases containing definite or specific nouns and adjectives

instances of the word "the" and its contextual usage

No Comments

No Known Activations