INDEX

Explanations

the word "No" with high activation values

oai_token-act-pair · gpt-3.5-turbo

repeated occurrences of the word "No."

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

rn

-0.67

RAFT

-0.64

MpServer

-0.64

knit

-0.63

tein

-0.62

CLOSE

-0.60

RANT

-0.59

adobe

-0.59

ULAR

-0.59

iership

-0.59

POSITIVE LOGITS

 kidding

1.08

 doubt

1.05

 wonder

1.00

vel

1.00

zzle

0.96

isy

0.96

 matter

0.95

 longer

0.92

emi

0.92

ct

0.90

Activations Density 0.060%

the word "No" with high activation values

repeated occurrences of the word "No."

No Comments

No Known Activations