INDEX

Explanations

mentions of individuals or entities by name

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ANC

-0.76

FORE

-0.69

urga

-0.64

ANCE

-0.63

RGB

-0.62

HAEL

-0.62

Wallet

-0.60

ELF

-0.60

ASED

-0.60

aneous

-0.59

POSITIVE LOGITS

cers

1.06

spe

1.02

nen

1.00

cil

0.96

cer

0.95

stant

0.94

mers

0.94

swer

0.91

oun

0.91

emouth

0.89

Activations Density 0.021%

mentions of individuals or entities by name

No Comments

No Known Activations