INDEX

Explanations

numerical data mentioned in reports or publications

oai_token-act-pair · gpt-3.5-turbo

references to data and reports, particularly about statistics and figures

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Reply

-0.60

uces

-0.60

 dislike

-0.58

Mods

-0.58

could

-0.58

 annoy

-0.57

instead

-0.56

 excess

-0.55

 inconvenience

-0.55

 beginnings

-0.54

POSITIVE LOGITS

 released

1.28

 compiled

1.19

 obtained

1.15

 commissioned

1.14

 published

1.10

 reviewed

1.08

 cited

1.06

 issued

1.04

 overseen

1.02

 supplied

1.01

Activations Density 0.136%

numerical data mentioned in reports or publications

references to data and reports, particularly about statistics and figures

No Comments

No Known Activations