INDEX

Explanations

references to destruction or related actions

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

words related to the concept of destruction or ending something

oai_token-act-pair · gpt-3.5-turbo Triggered by @danbraun

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.2.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

annis

-0.81

soType

-0.80

ickr

-0.79

çīĪ

-0.79

ullah

-0.78

cius

-0.77

enegger

-0.76

appa

-0.71

duino

-0.70

ortality

-0.67

POSITIVE LOGITS

structed

0.78

struction

0.77

ãĥĦ

0.77

ãĥĩãĤ£

0.76

roying

0.74

ppelin

0.72

dump

0.72

ãĥī

0.72

ãĥ¤

0.71

etsk

0.71

Activations Density 0.340%

references to destruction or related actions

words related to the concept of destruction or ending something

No Comments

No Known Activations