INDEX

Explanations

quantifiers and comparisons

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

aston

-0.70

Ãį

-0.69

may

-0.69

afia

-0.69

ccording

-0.67

elle

-0.65

ek

-0.65

ARE

-0.65

ãĤ¨

-0.65

POSITIVE LOGITS

 ours

0.89

 actual

0.88

 outright

0.80

 theirs

0.74

 hers

0.73

 otherwise

0.71

 ones

0.71

 necessarily

0.70

 yours

0.70

 nons

0.69

Activations Density 2.572%

quantifiers and comparisons

No Comments

No Known Activations