INDEX

Explanations

dialogue in a script

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

itol

-0.77

oling

-0.66

unin

-0.64

pointers

-0.63

etheless

-0.63

oche

-0.61

untarily

-0.59

iqu

-0.59

chev

-0.58

ov

-0.58

POSITIVE LOGITS

 Logged

0.75

 Lastly

0.66

Who

0.65

 Explain

0.64

 What

0.63

Has

0.61

 Does

0.59

yss

0.59

 Would

0.59

 Previous

0.58

Activations Density 10.039%

dialogue in a script

No Comments

No Known Activations