INDEX

Explanations

terms related to the concept of abstaining or refraining from certain actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

terms related to abstaining or refraining from certain actions

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

 guiActiveUnfocused

-0.74

esan

-0.71

 Spur

-0.70

 Printing

-0.69

 Tycoon

-0.67

videos

-0.67

ãĤ¨ãĥ«

-0.66

quickShipAvailable

-0.66

 Pioneer

-0.65

Plex

-0.64

POSITIVE LOGITS

 abst

1.07

rences

0.91

iencies

0.89

aye

0.86

iture

0.85

inent

0.84

itures

0.79

inance

0.78

arians

0.78

ention

0.77

Activations Density 0.013%

terms related to the concept of abstaining or refraining from certain actions or behaviors

terms related to abstaining or refraining from certain actions

No Comments

No Known Activations