INDEX

Explanations

numbers and symbols in a particular format

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics

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

claw

-0.62

prises

-0.57

igraph

-0.57

bern

-0.56

soDeliveryDate

-0.55

draw

-0.55

ODUCT

-0.54

worldly

-0.54

cue

-0.50

cro

-0.50

POSITIVE LOGITS

iola

0.63

luster

0.59

ãĤ¼ãĤ¦ãĤ¹

0.58

EVA

0.58

HAHA

0.58

oglu

0.57

ZE

0.56

ello

0.55

sic

0.55

reau

0.54

Activations Density 1.065%

numbers and symbols in a particular format

numerical data or statistics

No Comments

No Known Activations