INDEX

Explanations

words related to people's names

oai_token-act-pair · gpt-3.5-turbo

names of individuals or specific people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 RELE

-0.72

natureconservancy

-0.71

 prost

-0.69

COM

-0.68

TRA

-0.67

 INTER

-0.67

CLS

-0.67

 recomb

-0.66

 acron

-0.65

 sanct

-0.65

POSITIVE LOGITS

ovich

1.01

aga

1.00

ois

0.98

baum

0.98

ouf

0.97

ason

0.97

kson

0.97

idy

0.97

ault

0.97

oit

0.96

Activations Density 0.194%

words related to people's names

names of individuals or specific people

No Comments

No Known Activations