INDEX

Explanations

occurrences of numerical and quantifiable references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rawdownloadcloneembedreportprint

-0.74

++++++++++++++++

-0.71

è¦ļéĨĴ

-0.66

Cra

-0.63

 Leilan

-0.63

 includ

-0.62

 Canaver

-0.61

zai

-0.61

 indo

-0.60

hya

-0.59

POSITIVE LOGITS

awks

1.41

awk

1.36

orse

1.22

ouses

1.17

owler

1.09

ttp

1.05

ousand

1.01

undred

0.98

uffs

0.95

orns

0.94

Activations Density 0.009%

occurrences of numerical and quantifiable references

No Comments

No Known Activations

occurrences of numerical and quantifiable references

No Comments

No Known Activations