INDEX

Explanations

proper names, specifically the name "Sebastian."

oai_token-act-pair · gpt-3.5-turbo

names of individuals, particularly those associated with art and crime

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

robe

-0.89

marked

-0.84

rum

-0.82

acles

-0.81

sight

-0.81

ochond

-0.80

raq

-0.78

nings

-0.77

wich

-0.77

rug

-0.77

POSITIVE LOGITS

 Gomez

0.96

 Garcia

0.93

 Rossi

0.93

 Rodriguez

0.90

 Fernandez

0.90

 Santos

0.89

 Perez

0.88

 NiÃ±o

0.87

 Hernandez

0.87

 Antonio

0.86

Activations Density 0.042%

proper names, specifically the name "Sebastian."

names of individuals, particularly those associated with art and crime

No Comments

No Known Activations