INDEX

Explanations

references to numerical data or specifications

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

AUD

-0.76

Lud

-0.74

Vag

-0.70

 Gleaming

-0.69

ter

-0.68

 Guest

-0.67

 wedge

-0.67

 Gentleman

-0.66

 Spectre

-0.65

 ghost

-0.65

POSITIVE LOGITS

1.49

1.30

nine

1.03

0.99

0.96

Nine

0.93

0.90

 nine

0.90

0.89

Activations Density 0.030%

references to numerical data or specifications

No Comments

No Known Activations