INDEX

Explanations

occurrences of the verb "do" and its variations in various contexts

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

lights

-0.62

pac

-0.60

uses

-0.59

 Entered

-0.57

 Madagascar

-0.54

dayName

-0.54

mares

-0.51

 Prot

-0.51

ros

-0.51

sg

-0.51

POSITIVE LOGITS

ppel

0.96

lez

0.92

omsday

0.88

vet

0.82

ozy

0.78

omething

0.75

xy

0.75

berman

0.75

 likewise

0.74

 wonders

0.73

Activations Density 0.062%

occurrences of the verb "do" and its variations in various contexts

No Comments

No Known Activations