INDEX

Explanations

the phrase "Big" followed by a number

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Big" followed by numbers, indicating a focus on significant entities, brands, or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 confir

-0.90

istry

-0.82

theless

-0.78

idency

-0.78

cia

-0.72

ILA

-0.71

perty

-0.69

 autop

-0.67

yrim

-0.67

Dialogue

-0.66

POSITIVE LOGITS

gest

1.44

ger

1.21

wig

0.99

gie

0.99

gers

0.95

gins

0.94

 Brother

0.87

glers

0.86

GER

0.85

ging

0.85

Activations Density 0.024%

the phrase "Big" followed by a number

occurrences of the term "Big" followed by numbers, indicating a focus on significant entities, brands, or events

No Comments

No Known Activations