INDEX

Explanations

numerical data and values in the text

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

 unders

-0.76

CAM

-0.74

 polic

-0.68

 shutter

-0.66

 portrait

-0.66

 purse

-0.66

 framing

-0.65

 cottage

-0.65

 camer

-0.65

 Alexandra

-0.64

POSITIVE LOGITS

1.23

1.22

1.10

1.09

1.07

1.05

1.03

1.00

Activations Density 0.024%

numerical data and values in the text

No Comments

No Known Activations