INDEX

Explanations

instances of the word "decision" and its variations

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

ewitness

-0.82

rites

-0.71

antis

-0.66

ittens

-0.65

heres

-0.65

ateurs

-0.65

outh

-0.64

aired

-0.64

anti

-0.64

nces

-0.64

POSITIVE LOGITS

 decision

0.95

 regarding

0.92

 decisions

0.92

 wisely

0.89

 whether

0.86

 choices

0.84

 accordingly

0.83

 unilaterally

0.83

CHO

0.80

 choice

0.79

Activations Density 0.035%

instances of the word "decision" and its variations

No Comments

No Known Activations