INDEX

Explanations

instances where someone expresses a statement or opinion

oai_token-act-pair · gpt-3.5-turbo

instances of the word "voiced" and its variations, indicating expressions of opinion or concern

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

illard

-0.80

igsaw

-0.72

ney

-0.71

neys

-0.71

adr

-0.69

ionage

-0.67

 Journals

-0.66

addy

-0.65

rug

-0.65

igm

-0.64

POSITIVE LOGITS

 voiced

1.19

 voicing

1.04

 voice

1.01

 voices

1.00

 voic

0.97

 vocal

0.92

unci

0.88

 artic

0.86

 chords

0.85

voice

0.84

Activations Density 0.007%

instances where someone expresses a statement or opinion

instances of the word "voiced" and its variations, indicating expressions of opinion or concern

No Comments

No Known Activations