INDEX

Explanations

phrases related to weighing pros and cons in decision-making

oai_token-act-pair · gpt-3.5-turbo

concepts related to trade-offs and choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

deen

-0.71

aband

-0.68

ENTS

-0.68

miah

-0.66

rafted

-0.62

ufact

-0.62

oup

-0.61

reb

-0.60

den

-0.60

gments

-0.60

POSITIVE LOGITS

 between

1.37

between

1.14

 Between

1.01

otomy

0.92

 separating

0.91

BET

0.82

undrum

0.78

 favoring

0.77

 dilemma

0.74

 balancing

0.74

Activations Density 0.182%

phrases related to weighing pros and cons in decision-making

concepts related to trade-offs and choices

No Comments

No Known Activations