INDEX

Explanations

scientific names of specific species or genera

oai_token-act-pair · gpt-3.5-turbo

terms related to scientific classification and nomenclature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sheet

-0.83

boards

-0.78

sett

-0.73

¥ŀ

-0.72

essert

-0.68

ishers

-0.68

anche

-0.68

erer

-0.67

rought

-0.65

ownt

-0.65

POSITIVE LOGITS

aurus

1.14

CRIP

0.91

Rex

0.91

ource

0.90

 Aure

0.85

peed

0.85

pex

0.83

Magikarp

0.83

Rex

0.83

ername

0.82

Activations Density 0.043%

scientific names of specific species or genera

terms related to scientific classification and nomenclature

No Comments

No Known Activations