INDEX

Explanations

entities or proper nouns consisting of two words with the second word starting with a capital letter

oai_token-act-pair · gpt-3.5-turbo

instances of numerical data and statistical references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.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

nesday

-0.98

 withd

-0.88

 favour

-0.86

 favoured

-0.81

 undecided

-0.79

 indu

-0.78

 consecut

-0.78

 compr

-0.78

 undermin

-0.76

 destro

-0.76

POSITIVE LOGITS

 largeDownload

0.94

Rail

0.91

ccording

0.89

ÂłÂłÂłÂłÂłÂłÂłÂł

0.89

Okay

0.88

Disclaimer

0.88

Joined

0.86

Stat

0.85

Constructed

0.84

Loading

0.83

Activations Density 0.233%

entities or proper nouns consisting of two words with the second word starting with a capital letter

instances of numerical data and statistical references

No Comments

No Known Activations