INDEX

Explanations

phrases indicating involvement in activities or behaviors

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "engage" and its variations in context of various actions or activities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 emerges

-0.70

makers

-0.68

 entrants

-0.65

CVE

-0.63

 latch

-0.62

 headlined

-0.61

 suited

-0.61

 ported

-0.61

loo

-0.60

 upset

-0.60

POSITIVE LOGITS

ordinate

0.90

umbn

0.79

 conversation

0.78

ventory

0.76

 vain

0.72

cheon

0.71

adr

0.67

 accordance

0.67

offensive

0.67

jured

0.66

Activations Density 0.064%

phrases indicating involvement in activities or behaviors

occurrences of the word "engage" and its variations in context of various actions or activities

No Comments

No Known Activations