INDEX

Explanations

variations of the word "care" and its derivatives

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

dayName

-0.91

ottest

-0.65

req

-0.61

 compuls

-0.59

DCS

-0.58

 newsletters

-0.58

article

-0.58

ittered

-0.57

 appe

-0.56

 interf

-0.56

POSITIVE LOGITS

paren

0.94

kefeller

0.81

thro

0.80

fare

0.78

butt

0.78

ndra

0.78

eer

0.77

oop

0.74

lings

0.74

zan

0.73

Activations Density 0.004%

variations of the word "care" and its derivatives

No Comments

No Known Activations