INDEX

Explanations

time durations expressed in relation to a specific reference point

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

alogy

-0.67

ãĥ³

-0.67

NEY

-0.66

LOS

-0.66

cean

-0.66

ieri

-0.65

tera

-0.65

clerosis

-0.64

ulet

-0.63

 Dynamics

-0.63

POSITIVE LOGITS

 half

1.00

 halfway

0.94

 stellar

0.86

icable

0.77

 Â½

0.75

 ideal

0.74

whelming

0.74

stellar

0.74

 cents

0.73

 optimal

0.71

Activations Density 0.072%

time durations expressed in relation to a specific reference point

No Comments

No Known Activations