INDEX

Explanations

expressions indicating a negative preference or avoidance

oai_token-act-pair · gpt-3.5-turbo

statements expressing a desire or reluctance regarding a specific action

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

issance

-0.81

ework

-0.74

bard

-0.70

hiba

-0.70

soDeliveryDate

-0.69

 Enhancement

-0.69

metadata

-0.68

VERTISEMENT

-0.67

icol

-0.67

strength

-0.67

POSITIVE LOGITS

 anymore

0.93

 anybody

0.91

 anyone

0.85

 anything

0.85

reprene

0.83

nor

0.80

any

0.77

ANY

0.76

 necessarily

0.75

 surprises

0.73

Activations Density 0.041%

expressions indicating a negative preference or avoidance

statements expressing a desire or reluctance regarding a specific action

No Comments

No Known Activations