INDEX

Explanations

numeric values, particularly related to years and percentages

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

ivity

-0.85

ivities

-0.85

ique

-0.84

iques

-0.81

ãĤ¤ãĥĪ

-0.74

lier

-0.74

ional

-0.72

icles

-0.72

icular

-0.68

ically

-0.67

POSITIVE LOGITS

 externalToEVAOnly

1.03

0.92

0.86

0.85

mph

0.84

0.83

0.82

Activations Density 0.055%

numeric values, particularly related to years and percentages

No Comments

No Known Activations