INDEX

Explanations

technical terms related to biological experiments and procedures

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

ochond

-0.74

istrate

-0.66

ounded

-0.65

ophen

-0.62

 opin

-0.58

vale

-0.57

Override

-0.56

etitive

-0.56

ahu

-0.56

']

-0.55

POSITIVE LOGITS

1.34

0.92

 preferably

0.86

0.85

0.84

0.79

Activations Density 11.170%

technical terms related to biological experiments and procedures

No Comments

No Known Activations