INDEX

Explanations

terms related to low values or rankings

oai_token-act-pair · gpt-3.5-turbo

references to low quantities or levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 mirrors

-0.67

 dinosaur

-0.61

 chairs

-0.61

 attest

-0.60

 pieces

-0.59

 seeds

-0.58

 words

-0.58

ver

-0.57

 giant

-0.57

 arms

-0.56

POSITIVE LOGITS

low

4.30

Low

2.10

high

1.79

LOW

1.68

lower

1.64

Low

1.59

highest

1.37

 lows

1.33

worst

1.33

low

1.29

Activations Density 0.010%

terms related to low values or rankings

references to low quantities or levels

No Comments

No Known Activations