INDEX

Explanations

phrases related to actions or processes

oai_token-act-pair · gpt-3.5-turbo

phrases indicating relationships or connections

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

yd

-0.73

ophy

-0.71

cci

-0.66

JD

-0.65

amiya

-0.65

tri

-0.65

È

-0.64

ournal

-0.63

chant

-0.62

cro

-0.62

POSITIVE LOGITS

pload

0.74

 theirs

0.74

 Havana

0.69

 Fidel

0.66

 hers

0.65

 slavery

0.65

 rubble

0.64

Pin

0.64

 rout

0.60

 steroids

0.60

Activations Density 0.417%

phrases related to actions or processes

phrases indicating relationships or connections

No Comments

No Known Activations