INDEX

Explanations

names of people or organizations

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

ãĥł

-0.85

ãĥ´ãĤ¡

-0.80

ĸļ

-0.77

 unfocusedRange

-0.73

ãĤ´

-0.70

Zur

-0.69

igm

-0.65

 Expend

-0.63

OTOS

-0.63

pes

-0.62

POSITIVE LOGITS

igans

0.97

hunt

0.97

ewater

0.82

amac

0.80

igan

0.80

ework

0.78

stone

0.78

nian

0.76

iland

0.76

bang

0.75

Activations Density 11.720%

names of people or organizations

No Comments

No Known Activations