INDEX

Explanations

Specific actions or events that involve negative or controversial situations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ologically

-0.71

gery

-0.64

urb

-0.61

informed

-0.60

hid

-0.59

 disgu

-0.58

uana

-0.57

geries

-0.56

isa

-0.56

undai

-0.56

POSITIVE LOGITS

CLOSE

0.90

aign

0.61

UTERS

0.60

GROUND

0.60

 Skip

0.60

INGS

0.59

 ALSO

0.59

FIX

0.59

Interstitial

0.58

 Remastered

0.58

Activations Density 10.933%

Specific actions or events that involve negative or controversial situations

No Comments

No Known Activations