INDEX

Explanations

references to academic or scholarly content, possibly citations or references within a document

oai_token-act-pair · gpt-3.5-turbo

numerical values or symbols

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

 administr

-0.78

 manif

-0.71

ominated

-0.66

rium

-0.63

 quota

-0.63

isphere

-0.62

 neighb

-0.62

stood

-0.60

 itself

-0.59

 relocation

-0.59

POSITIVE LOGITS

 SHARES

1.23

 stitches

1.00

 Explicit

0.95

 Shares

0.94

 Pages

0.92

 Reasons

0.90

 Minutes

0.84

 mins

0.82

 Comments

0.80

th

0.80

Activations Density 0.071%

references to academic or scholarly content, possibly citations or references within a document

numerical values or symbols

No Comments

No Known Activations