INDEX

Explanations

references to specific weeks in a sports season

oai_token-act-pair · gpt-3.5-turbo

mentions of specific weeks or time periods in a sports context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ifice

-0.65

 suspic

-0.64

 princ

-0.63

 enthusi

-0.62

 cursor

-0.61

Frameworks

-0.61

 Aires

-0.60

 drowning

-0.60

 drowned

-0.59

cas

-0.59

POSITIVE LOGITS

DAY

1.12

days

1.10

day

0.94

night

0.89

hof

0.89

ends

0.87

hoff

0.81

aday

0.80

end

0.76

orrow

0.76

Activations Density 0.033%

references to specific weeks in a sports season

mentions of specific weeks or time periods in a sports context

No Comments

No Known Activations