INDEX

Explanations

proper nouns related to people, places, or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and brands

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anwhile

-0.72

OPLE

-0.71

 charge

-0.71

 separatist

-0.70

ħĭ

-0.68

 retaliate

-0.68

etheless

-0.67

ãĥ¼ãĥĨ

-0.67

 depreciation

-0.66

 grievance

-0.65

POSITIVE LOGITS

ona

1.06

isha

0.94

oya

0.93

amo

0.90

ado

0.90

leys

0.90

ley

0.89

inda

0.88

onda

0.87

udos

0.87

Activations Density 0.467%

proper nouns related to people, places, or entities

proper nouns, particularly names and brands

No Comments

No Known Activations