INDEX

Explanations

instances of phrases related to difficult or challenging 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

 Logged

-0.57

STA

-0.56

 Crusher

-0.50

maid

-0.46

CVE

-0.46

0000000000000000

-0.45

 demol

-0.44

wife

-0.43

allow

-0.43

MU

-0.43

POSITIVE LOGITS

 periphery

0.76

 vicinity

0.69

animate

0.67

between

0.63

 continuum

0.60

 somew

0.56

accessible

0.56

swick

0.56

ibaba

0.55

ordinate

0.55

Activations Density 14.125%

instances of phrases related to difficult or challenging situations

No Comments

No Known Activations