INDEX

Explanations

references to "Guggenheim"

oai_token-act-pair · gpt-3.5-turbo

the presence of the term "Guggenheim."

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

peak

-0.72

 Leilan

-0.71

 wards

-0.69

cape

-0.65

 compr

-0.63

 Divinity

-0.61

 intensive

-0.60

 wart

-0.60

 choking

-0.59

 bron

-0.59

POSITIVE LOGITS

glers

1.58

ging

1.27

ged

1.25

gery

1.23

gers

1.17

uay

1.17

uese

1.15

ger

1.08

nant

0.95

gin

0.91

Activations Density 0.020%

references to "Guggenheim"

the presence of the term "Guggenheim."

No Comments

No Known Activations