INDEX

Explanations

phrases related to scoring goals in sports

oai_token-act-pair · gpt-3.5-turbo

phrases related to scoring or goals in sports

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

é¾įå¥ĳå£«

-0.83

idav

-0.83

ratulations

-0.76

azeera

-0.74

merce

-0.73

ipedia

-0.70

ItemTracker

-0.70

irm

-0.69

tymology

-0.69

PLA

-0.69

POSITIVE LOGITS

 afar

1.32

 abroad

0.97

 inside

0.95

 scrimmage

0.87

 anywhere

0.83

 scratch

0.82

 elsewhere

0.81

 midfield

0.80

 atop

0.79

 across

0.76

Activations Density 0.090%

phrases related to scoring goals in sports

phrases related to scoring or goals in sports

No Comments

No Known Activations