INDEX

Explanations

words or phrases related to cognitive dissonance, misunderstanding, or lack of clarity in a text

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rera

-0.72

bors

-0.72

 promot

-0.70

yss

-0.70

dain

-0.69

eatures

-0.69

thin

-0.68

 conclud

-0.66

ternity

-0.65

inth

-0.65

POSITIVE LOGITS

ingly

1.04

 Leilan

0.94

 confuse

0.87

ively

0.81

fully

0.78

INESS

0.77

 Beir

0.75

 confusion

0.75

ly

0.74

ilde

0.74

Activations Density 7.984%

words or phrases related to cognitive dissonance, misunderstanding, or lack of clarity in a text

No Comments

No Known Activations