INDEX

Explanations

numerals indicating the frequency of an action or event

oai_token-act-pair · gpt-3.5-turbo

phrases that express repetition or frequency of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 heirs

-0.79

Marginal

-0.75

rights

-0.72

Reviewer

-0.70

XT

-0.69

 Flavoring

-0.67

yright

-0.66

atorium

-0.66

Accessory

-0.66

uld

-0.65

POSITIVE LOGITS

cale

0.92

manship

0.80

entimes

0.80

Ago

0.77

terness

0.71

coded

0.71

interstitial

0.70

TER

0.69

points

0.68

theless

0.68

Activations Density 0.028%

numerals indicating the frequency of an action or event

phrases that express repetition or frequency of events

No Comments

No Known Activations