INDEX

Explanations

names of people or places followed by a verb in past tense

oai_token-act-pair · gpt-3.5-turbo

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

flies

-0.82

 Newman

-0.81

iel

-0.77

 Robo

-0.75

zl

-0.74

Moe

-0.74

MO

-0.74

RL

-0.74

 Kissinger

-0.73

 Milky

-0.73

POSITIVE LOGITS

AT

1.78

at

1.66

ats

1.51

aton

1.40

atis

1.38

ati

1.35

atum

1.35

atar

1.33

ata

1.33

ATA

1.32

Activations Density 0.214%

names of people or places followed by a verb in past tense

No Comments

No Known Activations