INDEX

Explanations

references to drugs or medications containing "amp" in their names

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "amp"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

SHIP

-1.05

BLIC

-0.82

ĪĴ

-0.71

ignty

-0.71

 Kers

-0.63

ÃįÃį

-0.63

 resemblance

-0.63

ALLY

-0.63

 obser

-0.62

çĭ

-0.62

POSITIVE LOGITS

hetamine

1.24

agne

1.14

aign

1.11

oons

1.05

shire

1.01

reys

0.98

osite

0.94

owered

0.94

ierre

0.93

agn

0.93

Activations Density 0.036%

references to drugs or medications containing "amp" in their names

occurrences of the word "amp"

No Comments

No Known Activations