INDEX

Explanations

the word "much" and its varying 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

İĭ

-0.81

ologies

-0.75

 Tags

-0.74

etts

-0.73

emy

-0.71

raid

-0.70

opers

-0.69

emies

-0.68

pas

-0.68

ATURES

-0.68

POSITIVE LOGITS

ado

0.99

 else

0.81

NESS

0.79

 resemblance

0.72

 misinformation

0.72

body

0.71

 simpler

0.71

 unspecified

0.70

 stricter

0.70

 attention

0.69

Activations Density 0.037%

the word "much" and its varying contexts

No Comments

No Known Activations