INDEX

Explanations

numbers, particularly those indicating a specific quantity or range

oai_token-act-pair · gpt-3.5-turbo

numerical data, particularly ranges and quantities

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

 conduc

-0.65

 unnecess

-0.60

 correctly

-0.57

 alike

-0.55

 whatsoever

-0.54

 notor

-0.53

 unfocusedRange

-0.53

 therap

-0.53

Reviewer

-0.53

 behavi

-0.51

POSITIVE LOGITS

]-

0.79

%-

0.79

-$

0.72

and

0.71

gee

0.71

ties

0.71

endor

0.64

brow

0.62

]"

0.62

and

0.62

Activations Density 0.084%

numbers, particularly those indicating a specific quantity or range

numerical data, particularly ranges and quantities

No Comments

No Known Activations