INDEX

Explanations

proper nouns related to people or entities

oai_token-act-pair · gpt-3.5-turbo

words related to various types of entities and people, particularly names and significant abbreviations

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

CBI

-0.71

[*]

-0.67

Balt

-0.62

 mantle

-0.61

 questioning

-0.58

 deed

-0.58

ãĥ¼ãĥĨ

-0.57

ECTION

-0.56

 sheet

-0.56

 slic

-0.56

POSITIVE LOGITS

waukee

1.00

nih

0.93

gage

0.88

intosh

0.82

htar

0.75

ICAN

0.74

nesota

0.73

ifest

0.73

udi

0.72

emonic

0.71

Activations Density 0.116%

proper nouns related to people or entities

words related to various types of entities and people, particularly names and significant abbreviations

No Comments

No Known Activations