INDEX

Explanations

capital letters that are at the highest possible activation value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "X" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kson

-0.75

getic

-0.72

beh

-0.68

Ú

-0.65

 behavi

-0.65

enance

-0.60

 appe

-0.60

à¨

-0.59

à©

-0.59

keepers

-0.59

POSITIVE LOGITS

VII

1.41

III

1.36

peria

1.32

avier

1.32

IX

1.24

VI

1.19

II

1.18

IV

1.13

cellence

1.11

ML

1.10

Activations Density 0.052%

capital letters that are at the highest possible activation value

occurrences of the letter "X" in various contexts

No Comments

No Known Activations