INDEX

Explanations

expressions indicating a key point or critical aspect in a discussion

oai_token-act-pair · gpt-3.5-turbo

references to the presence of significant points or concepts in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

itialized

-0.64

visors

-0.64

 Eclipse

-0.61

ggle

-0.55

UTH

-0.54

llor

-0.54

 bowel

-0.54

acci

-0.54

 Spending

-0.53

 Heights

-0.53

POSITIVE LOGITS

abouts

1.63

tical

1.42

tics

1.37

tic

1.24

here

0.79

with

0.74

 guiActiveUn

0.74

upon

0.72

fires

0.72

adays

0.69

Activations Density 0.047%

expressions indicating a key point or critical aspect in a discussion

references to the presence of significant points or concepts in the text

No Comments

No Known Activations