INDEX

Explanations

female names

oai_token-act-pair · gpt-3.5-turbo

proper names, particularly focusing on the names of individuals

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

ounding

-0.78

direction

-0.76

awar

-0.74

istani

-0.73

papers

-0.69

zag

-0.69

haps

-0.69

cffff

-0.69

tumblr

-0.68

roph

-0.67

POSITIVE LOGITS

 Gomez

1.06

 Olson

1.00

 Kelley

0.99

Roe

0.97

 Roberts

0.97

 Robinson

0.96

 Moore

0.95

 Rivera

0.92

 Hansen

0.91

 Carey

0.91

Activations Density 0.145%

female names

proper names, particularly focusing on the names of individuals

No Comments

No Known Activations