INDEX

Explanations

superlatives and comparative terms such as "easiest," "closest," "best," and "most."

oai_token-act-pair · gpt-3.5-turbo

terms related to ease and quality of solutions or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

azard

-0.76

avis

-0.70

ammed

-0.68

senal

-0.66

discrimination

-0.64

ustom

-0.64

ipel

-0.63

apesh

-0.63

ilater

-0.62

historic

-0.62

POSITIVE LOGITS

 thing

0.89

 downside

0.88

 question

0.87

 reason

0.82

 difference

0.79

 explanation

0.79

 drawback

0.78

 exception

0.77

 straw

0.77

 caveat

0.77

Activations Density 0.173%

superlatives and comparative terms such as "easiest," "closest," "best," and "most."

terms related to ease and quality of solutions or options

No Comments

No Known Activations