INDEX

Explanations

descriptions of exploratory travels or voyages

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

verage

-0.70

ouf

-0.61

vette

-0.61

åº

-0.60

Enlarge

-0.60

 arrivals

-0.59

SEE

-0.58

clip

-0.57

acca

-0.56

ADVERTISEMENT

-0.56

POSITIVE LOGITS

 raining

0.62

chy

0.59

Matrix

0.57

washer

0.57

ohm

0.55

LESS

0.55

 acronym

0.54

 hurts

0.54

unes

0.53

raw

0.52

Activations Density 17.387%

descriptions of exploratory travels or voyages

No Comments

No Known Activations