INDEX

Explanations

verbs related to boasting or expressing pride

oai_token-act-pair · gpt-3.5-turbo

variations of the word "brag" and related concepts

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

 captcha

-0.79

ãĤ¡

-0.74

ãĥĥãĤ¯

-0.70

-0.68

ãĥ¯ãĥ³

-0.67

ãĤ¨

-0.67

Ļ½

-0.65

ãĥĬ

-0.64

ictionary

-0.63

ãĤ»

-0.63

POSITIVE LOGITS

doms

0.97

antly

0.94

 loudly

0.89

 confidently

0.83

 boasted

0.80

 bragging

0.76

 about

0.75

ulate

0.74

acious

0.74

 boasts

0.72

Activations Density 0.044%

verbs related to boasting or expressing pride

variations of the word "brag" and related concepts

No Comments

No Known Activations