INDEX

Explanations

words related to scoring, rewards, and progression in a competitive context

oai_token-act-pair · gpt-3.5-turbo

terms related to scoring or gaining points in games

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

OSP

-0.69

eatures

-0.63

 unanim

-0.63

odynam

-0.63

 Franch

-0.62

 Babel

-0.62

 enthusi

-0.62

bod

-0.61

inson

-0.61

 skelet

-0.60

POSITIVE LOGITS

 Gained

1.17

 expended

1.16

 accumulated

1.13

 accrued

1.11

 deducted

1.08

 gained

1.07

 earned

1.07

 awarded

1.05

 allocated

1.03

 allotted

0.98

Activations Density 0.278%

words related to scoring, rewards, and progression in a competitive context

terms related to scoring or gaining points in games

No Comments

No Known Activations