INDEX

Explanations

words related to specific geographic locations

oai_token-act-pair · gpt-3.5-turbo

words related to specific locations, objects, or entities within a context

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

 Qiao

-0.78

 DRAG

-0.62

uterte

-0.61

 Barker

-0.59

 Dart

-0.59

 BaseType

-0.58

 Carbuncle

-0.57

 Curry

-0.57

 Nguyen

-0.57

0000000000000000

-0.56

POSITIVE LOGITS

ãĤ¼

0.78

insk

0.77

ewski

0.75

ioch

0.73

zynski

0.72

nis

0.71

icter

0.71

yna

0.69

nik

0.65

united

0.64

Activations Density 0.286%

words related to specific geographic locations

words related to specific locations, objects, or entities within a context

No Comments

No Known Activations