INDEX

Explanations

cities, locations, or geographical places

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to cities and locations

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

 subscript

-0.72

cedented

-0.71

Downloadha

-0.67

etheless

-0.66

nces

-0.65

aciously

-0.64

 skept

-0.61

voc

-0.61

 ende

-0.60

 glim

-0.60

POSITIVE LOGITS

minster

0.77

ankind

0.72

 fame

0.72

areth

0.71

hess

0.71

burgh

0.69

amer

0.68

bart

0.67

sburg

0.65

 Manor

0.64

Activations Density 0.382%

cities, locations, or geographical places

proper nouns related to cities and locations

No Comments

No Known Activations