INDEX

Explanations

text related to names, naming, and naming disputes

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate naming or renaming entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 throughput

-0.84

wage

-0.77

overty

-0.75

anasia

-0.73

prison

-0.72

Progress

-0.72

 mitigation

-0.71

Duration

-0.71

capacity

-0.71

ileaks

-0.70

POSITIVE LOGITS

 naming

1.76

 nickname

1.62

 surn

1.59

 moniker

1.57

 name

1.50

 Names

1.50

 surname

1.50

 initials

1.49

 rename

1.48

 names

1.47

Activations Density 0.766%

text related to names, naming, and naming disputes

phrases that indicate naming or renaming entities

No Comments

No Known Activations