INDEX

Explanations

proper nouns related to news headlines or articles

oai_token-act-pair · gpt-3.5-turbo

phrases or terms related to significant statistics or numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

eca

-0.66

 anyways

-0.64

 prioritize

-0.62

TBD

-0.61

 ignor

-0.59

 happ

-0.59

 upstream

-0.59

 incent

-0.58

 integ

-0.58

 inactive

-0.57

POSITIVE LOGITS

SPONSORED

1.13

Writing

1.08

Speaking

0.99

Scroll

0.96

Hundreds

0.92

BBC

0.91

Britain

0.91

Phot

0.90

Actor

0.89

Asked

0.89

Activations Density 0.560%

proper nouns related to news headlines or articles

phrases or terms related to significant statistics or numerical data

No Comments

No Known Activations