INDEX

Explanations

names of specific locations

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 digit

-0.69

 perman

-0.64

inyl

-0.63

 textual

-0.60

Wikipedia

-0.57

letter

-0.56

 relational

-0.56

ronic

-0.56

itionally

-0.56

RW

-0.55

POSITIVE LOGITS

 airspace

1.00

 yesterday

0.83

 skies

0.83

 Springs

0.83

 tonight

0.82

 Gardens

0.79

 Harbor

0.77

 Heights

0.76

 Meadows

0.76

 Valley

0.74

Activations Density 0.208%

names of specific locations

No Comments

No Known Activations