INDEX

Explanations

phrases related to ice hockey goalkeeping statistics, particularly save percentages and the number of saves made

oai_token-act-pair · gpt-3.5-turbo

references to saves in hockey statistics

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

Else

-0.94

yond

-0.74

enberg

-0.72

RY

-0.72

cale

-0.71

naire

-0.67

issance

-0.63

ounced

-0.63

hester

-0.63

orporated

-0.63

POSITIVE LOGITS

éĹĺ

0.87

 Cache

0.74

TOR

0.73

 Marcos

0.66

 Sanctuary

0.66

 Save

0.65

orage

0.64

Save

0.64

 Shelter

0.63

 Deposit

0.61

Activations Density 0.018%

phrases related to ice hockey goalkeeping statistics, particularly save percentages and the number of saves made

references to saves in hockey statistics

No Comments

No Known Activations