INDEX

Explanations

references to specific locations or landmarks

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

éĹĺ

-0.89

ħĭ

-0.87

 nomine

-0.86

 actionGroup

-0.85

sburgh

-0.84

 Skydragon

-0.78

pherd

-0.78

Pie

-0.74

EStream

-0.71

VALUE

-0.71

POSITIVE LOGITS

rah

1.09

lington

1.06

ien

1.04

agon

1.02

geon

0.96

ques

0.95

aya

0.95

izon

0.93

jan

0.92

bor

0.90

Activations Density 6.560%

references to specific locations or landmarks

No Comments

No Known Activations