INDEX

Explanations

words related to decisions or choices with an emphasis on consequences

oai_token-act-pair · gpt-3.5-turbo

concepts related to value and decision-making

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Cosponsors

-0.85

ãĥīãĥ©

-0.83

azines

-0.79

Sources

-0.79

ideos

-0.78

orks

-0.78

ombies

-0.77

mes

-0.75

paces

-0.74

urations

-0.74

POSITIVE LOGITS

 worth

1.03

 unto

1.02

 breaker

1.02

 worthy

0.97

brainer

0.94

 borne

0.94

 impossibility

0.92

 reminder

0.91

breaker

0.87

less

0.84

Activations Density 0.283%

words related to decisions or choices with an emphasis on consequences

concepts related to value and decision-making

No Known Activations