INDEX

Explanations

phrases related to following or copying someone's lead or actions

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

cer

-0.71

voy

-0.65

bodied

-0.65

atonin

-0.64

hya

-0.64

pmwiki

-0.63

inese

-0.63

ldom

-0.63

flo

-0.63

vere

-0.63

POSITIVE LOGITS

 suit

1.01

 closely

0.92

 footsteps

0.79

İĭ

0.73

pend

0.71

ansen

0.69

suit

0.68

 instructions

0.68

edient

0.68

 Suit

0.65

Activations Density 1.498%

phrases related to following or copying someone's lead or actions

No Comments

No Known Activations