INDEX

Explanations

mentions of the name "Els" with varying activation strengths

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names or terms related to 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

 Occupations

-0.67

isites

-0.65

 Seym

-0.64

--+

-0.64

scribed

-0.63

 Augusta

-0.62

ãĥ¼ãĥĨ

-0.61

 Sakuya

-0.60

 Skydragon

-0.60

repe

-0.59

POSITIVE LOGITS

inki

1.10

pace

1.08

bach

0.99

warm

0.97

ength

0.95

hof

0.95

ink

0.91

kamp

0.91

ounge

0.91

kie

0.90

Activations Density 0.016%

mentions of the name "Els" with varying activation strengths

mentions of specific names or terms related to individuals

No Comments

No Known Activations