INDEX

Explanations

references to locations or places

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

inventoryQuantity

-0.77

catentry

-0.71

ahime

-0.69

mble

-0.66

coon

-0.62

anish

-0.61

 Decay

-0.59

MM

-0.59

 Kaiser

-0.59

Counter

-0.58

POSITIVE LOGITS

abouts

1.51

tical

1.51

tics

1.47

tic

1.16

 illegally

0.84

with

0.76

yers

0.74

to

0.69

fires

0.66

adays

0.65

Activations Density 0.049%

references to locations or places

No Comments

No Known Activations