INDEX

Explanations

proper names or terms related to science, history, or academia

oai_token-act-pair · gpt-3.5-turbo

Latin or Latin-derived suffixes and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ishers

-0.91

ishing

-0.81

ished

-0.79

sheet

-0.79

writers

-0.72

estine

-0.72

est

-0.71

ership

-0.71

ston

-0.71

ishment

-0.71

POSITIVE LOGITS

aurus

1.08

pex

0.87

CRIP

0.87

peed

0.87

cular

0.84

0.83

 Aure

0.82

 Mons

0.80

ource

0.79

 Mund

0.77

Activations Density 0.113%

proper names or terms related to science, history, or academia

Latin or Latin-derived suffixes and terms

No Comments

No Known Activations