INDEX

Explanations

numbers indicating units of measurement

oai_token-act-pair · gpt-3.5-turbo

references to measurement units and data values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 bonuses

-0.85

 amounts

-0.77

 unmist

-0.76

 Ober

-0.74

 redist

-0.74

 mimic

-0.73

 reminders

-0.72

 numbers

-0.71

 Vander

-0.71

 terminating

-0.71

POSITIVE LOGITS

hr

1.60

sec

1.50

sq

1.37

hour

1.34

rev

1.33

lbs

1.32

lb

1.30

kg

1.28

each

1.27

mol

1.25

Activations Density 0.030%

numbers indicating units of measurement

references to measurement units and data values

No Comments

No Known Activations