INDEX

Explanations

words related to specific names, terms, or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific individuals and entities in legal or political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

cies

-0.82

eous

-0.81

LEASE

-0.72

liness

-0.69

lisher

-0.68

wich

-0.68

iHUD

-0.68

ederal

-0.67

ingham

-0.65

thodox

-0.64

POSITIVE LOGITS

 Scala

0.89

anus

0.86

craft

0.74

orem

0.74

 Slug

0.69

ucci

0.69

 ILCS

0.68

=#

0.68

 Yard

0.68

chio

0.67

Activations Density 0.013%

words related to specific names, terms, or entities

proper nouns related to specific individuals and entities in legal or political contexts

No Comments

No Known Activations