INDEX

Explanations

names of specific individuals, particularly focusing on the name "Haley."

oai_token-act-pair · gpt-3.5-turbo

mentions of specific political figures or personalities

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

orate

-0.90

uria

-0.90

istically

-0.89

iety

-0.88

olith

-0.85

alogue

-0.85

istry

-0.83

urious

-0.80

ological

-0.80

ising

-0.80

POSITIVE LOGITS

tin

0.70

 Mellon

0.66

éĹĺ

0.65

CBO

0.64

 Haley

0.64

 Seat

0.63

 Methodist

0.62

 Crosby

0.60

 Garrett

0.60

 Belle

0.59

Activations Density 0.068%

names of specific individuals, particularly focusing on the name "Haley."

mentions of specific political figures or personalities

No Comments

No Known Activations