INDEX

Explanations

phrases related to locations or directions

oai_token-act-pair · gpt-3.5-turbo

references to hands and their positions in various contexts

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

vell

-0.77

uni

-0.77

urity

-0.74

anamo

-0.70

endez

-0.69

idian

-0.66

aturday

-0.66

qqa

-0.65

burgh

-0.65

ournal

-0.64

POSITIVE LOGITS

lers

1.07

shake

0.90

ling

0.84

%%%%

0.80

erers

0.75

maid

0.73

--------------------------------------------------------

0.72

legate

0.70

ners

0.68

held

0.67

Activations Density 0.009%

phrases related to locations or directions

references to hands and their positions in various contexts

No Comments

No Known Activations