INDEX

Explanations

instances of the phrase "bona fide" and related terms

oai_token-act-pair · gpt-3.5-turbo

special characters or non-standard text references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

alus

-0.96

matic

-0.75

alia

-0.75

ary

-0.73

ulus

-0.72

aron

-0.72

RAM

-0.71

iple

-0.71

alys

-0.70

abase

-0.70

POSITIVE LOGITS

Ñ

0.93

ÑĤ

0.90

Ñĥ

0.87

ignt

0.86

ÑĢ

0.84

Ð´

0.84

Ð¼

0.84

ãĥĥãĥī

0.80

Ñģ

0.80

Ð»

0.78

Activations Density 0.011%

instances of the phrase "bona fide" and related terms

special characters or non-standard text references

No Comments

No Known Activations