INDEX

Explanations

phrases related to opinions or analysis

oai_token-act-pair · gpt-3.5-turbo

critical assessments or strong opinions about events or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

iage

-0.73

 ALWAYS

-0.71

awa

-0.69

aido

-0.68

 Flavoring

-0.68

 sacrific

-0.67

 Dise

-0.66

 Diseases

-0.65

anges

-0.65

prus

-0.63

POSITIVE LOGITS

 tone

0.86

 rhetorical

0.84

 undersc

0.80

 applause

0.79

hearted

0.79

 diplomatic

0.78

plom

0.76

 journalistic

0.75

 underscore

0.71

 alarms

0.71

Activations Density 0.833%

phrases related to opinions or analysis

critical assessments or strong opinions about events or decisions

No Comments

No Known Activations