INDEX

Explanations

the term "similarly" and variations indicating comparison or similarity in context

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

 Picks

-0.71

ender

-0.69

wives

-0.67

 Vendor

-0.67

 Cause

-0.66

Klu

-0.66

 Mouth

-0.66

 Payment

-0.65

 Benson

-0.64

 Sale

-0.64

POSITIVE LOGITS

 situated

1.41

 inclined

1.04

 sized

0.98

 shaped

0.95

 minded

0.93

 themed

0.88

 positioned

0.88

 tuned

0.85

 exting

0.84

 equipped

0.84

Activations Density 0.010%

the term "similarly" and variations indicating comparison or similarity in context

No Comments

No Known Activations