INDEX

Explanations

questions or phrases related to quantifying or measuring something

oai_token-act-pair · gpt-3.5-turbo

phrases that ask about quantification or estimation of value

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

İĭ

-0.93

Ń·

-0.91

swick

-0.82

ATURES

-0.78

strate

-0.76

ħĭ

-0.76

umbn

-0.76

pherd

-0.76

idon

-0.74

ivas

-0.73

POSITIVE LOGITS

 mileage

0.88

 money

0.87

 else

0.85

 extent

0.83

 damage

0.82

 attention

0.79

 elapsed

0.79

 influence

0.78

 firepower

0.77

 overlap

0.76

Activations Density 0.034%

questions or phrases related to quantifying or measuring something

phrases that ask about quantification or estimation of value

No Comments

No Known Activations