INDEX

Explanations

information related to shields in a combat or fighting context

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

gres

-0.77

iasco

-0.73

cause

-0.69

 Helpful

-0.69

orie

-0.68

 âĸº

-0.67

pheus

-0.66

jad

-0.66

 Judicial

-0.65

ĸļ

-0.64

POSITIVE LOGITS

heed

0.78

igans

0.77

 shield

0.76

 maiden

0.76

 shields

0.73

maid

0.72

abies

0.69

lain

0.68

buster

0.67

ades

0.66

Activations Density 6.576%

information related to shields in a combat or fighting context

No Comments

No Known Activations