INDEX

Explanations

subjects related to handedness, specifically identifying "left-handed" mentions

oai_token-act-pair · gpt-3.5-turbo

references to handedness, particularly "left-handed" and "right-handed" distinctions

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

anamo

-0.98

burgh

-0.82

CHAT

-0.82

raltar

-0.79

idian

-0.77

oother

-0.77

ĸļ

-0.76

ublic

-0.76

qqa

-0.76

liam

-0.75

POSITIVE LOGITS

 nodd

1.02

ness

0.95

 clutch

0.86

handed

0.76

 clut

0.76

 luggage

0.74

 dexterity

0.71

nesses

0.71

 barb

0.70

 thumb

0.69

Activations Density 0.022%

subjects related to handedness, specifically identifying "left-handed" mentions

references to handedness, particularly "left-handed" and "right-handed" distinctions

No Comments

No Known Activations