INDEX

Explanations

words related to characters and their activities in narratives

oai_token-act-pair · gpt-4o-mini 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

 surpr

-0.73

 seiz

-0.69

 welf

-0.64

 lapse

-0.62

 exha

-0.61

 flourishing

-0.61

 concess

-0.61

 necessities

-0.60

 carbohyd

-0.60

 subsequ

-0.60

POSITIVE LOGITS

ansky

0.81

dot

0.78

oslav

0.76

wagen

0.75

roid

0.74

lings

0.73

puff

0.73

idon

0.72

lator

0.71

Quote

0.71

Activations Density 0.265%

words related to characters and their activities in narratives

No Comments

No Known Activations