INDEX

Explanations

locations and technical terms related to software development

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names related to organizations, places, and specific entities

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

hower

-0.72

ãĥĦ

-0.72

theless

-0.71

 Kinnikuman

-0.66

 Celt

-0.62

assian

-0.60

 Kessler

-0.59

WHO

-0.57

ITNESS

-0.56

 Garr

-0.55

POSITIVE LOGITS

edIn

0.85

matically

0.81

ently

0.81

hett

0.76

arily

0.71

itia

0.71

pport

0.68

udeb

0.68

tarians

0.68

everal

0.64

Activations Density 0.652%

locations and technical terms related to software development

proper nouns and names related to organizations, places, and specific entities

No Comments

No Known Activations