INDEX

Explanations

quantitative expressions of completeness or certainty

oai_token-act-pair · gpt-3.5-turbo

references to the percentage of certainty or confidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olas

-0.78

rift

-0.66

 brill

-0.64

letal

-0.63

mare

-0.59

igham

-0.58

lihood

-0.58

 attraction

-0.56

 obscurity

-0.55

 Behavior

-0.55

POSITIVE LOGITS

1.24

%"

1.22

1.18

%.

1.13

%:

1.13

%,

1.11

%;

1.09

Mbps

1.05

 percent

1.04

%-

1.03

Activations Density 0.062%

quantitative expressions of completeness or certainty

references to the percentage of certainty or confidence

No Comments

No Known Activations