INDEX

Explanations

words related to detachment and alienation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

frey

-0.74

MAT

-0.71

iop

-0.65

fair

-0.63

umbers

-0.62

SourceFile

-0.61

zag

-0.59

emet

-0.58

Unix

-0.58

orously

-0.57

POSITIVE LOGITS

 from

0.91

owship

0.84

 FROM

0.82

 altogether

0.80

 unwanted

0.78

 overboard

0.74

from

0.72

 Syndrome

0.72

ients

0.71

frog

0.71

Activations Density 0.067%

words related to detachment and alienation

No Comments

No Known Activations