INDEX

Explanations

words related to voting

oai_token-act-pair · gpt-3.5-turbo

occurrences of the token "ote."

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

 slow

-0.69

 Slow

-0.64

 uninsured

-0.64

 uneven

-0.60

 Furious

-0.60

 unexplained

-0.60

 frustrations

-0.59

Lat

-0.59

 riots

-0.59

 divorce

-0.59

POSITIVE LOGITS

ote

4.53

otes

2.98

OTE

2.00

oting

1.89

oted

1.81

otal

1.58

ota

1.53

otic

1.45

ot

1.40

oters

1.31

Activations Density 0.010%

words related to voting

occurrences of the token "ote."

No Comments

No Known Activations