INDEX

Explanations

phrases or statements related to justification or validation

oai_token-act-pair · gpt-3.5-turbo

discussions surrounding justification and validity in various contexts

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

pmwiki

-0.71

 Gutenberg

-0.69

emi

-0.65

opathy

-0.65

pee

-0.65

hub

-0.64

Services

-0.64

yss

-0.64

uddy

-0.64

xia

-0.64

POSITIVE LOGITS

 indignation

0.90

 justified

0.84

ensibly

0.80

 justifies

0.78

 ignorance

0.73

aneously

0.72

 justification

0.72

 outrage

0.70

 condemnation

0.69

ifiable

0.69

Activations Density 0.015%

phrases or statements related to justification or validation

discussions surrounding justification and validity in various contexts

No Comments

No Known Activations