INDEX

Explanations

relevant nouns or noun phrases related to law, educational assessments, news & polling, social events, and medical practices

oai_token-act-pair · gpt-3.5-turbo

key terms related to legal and administrative processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

mpire

-0.71

heid

-0.70

 inflamm

-0.65

 unprotected

-0.64

wcs

-0.63

uilt

-0.63

venge

-0.63

ãĤ¤ãĥĪ

-0.63

perty

-0.63

pron

-0.62

POSITIVE LOGITS

 summarizes

0.79

 concludes

0.78

 recommends

0.70

 emphasizes

0.66

 illustrates

0.64

arten

0.62

 eluc

0.61

 encourages

0.61

 suggests

0.61

 underscores

0.60

Activations Density 0.937%

relevant nouns or noun phrases related to law, educational assessments, news & polling, social events, and medical practices

key terms related to legal and administrative processes

No Comments

No Known Activations