INDEX

Explanations

terms related to improvement or enhancement

oai_token-act-pair · gpt-3.5-turbo

instances of the word "boost" and its related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

©¶æ

-0.80

rors

-0.73

 Mortal

-0.71

________________

-0.69

________________________________

-0.69

________________________

-0.68

RAW

-0.67

 Antiqu

-0.66

 WATCHED

-0.65

present

-0.65

POSITIVE LOGITS

 boost

1.01

 boosting

0.99

boost

0.96

 boosts

0.88

 Boost

0.83

 boosted

0.79

avorite

0.77

 absor

0.76

xual

0.76

 boosters

0.75

Activations Density 0.011%

terms related to improvement or enhancement

instances of the word "boost" and its related contexts

No Comments

No Known Activations