INDEX

Explanations

tags or categories listed in a text

oai_token-act-pair · gpt-3.5-turbo

references to tags and categorization 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ITNESS

-0.88

owship

-0.71

thritis

-0.71

awar

-0.71

thren

-0.64

croft

-0.63

 Pradesh

-0.62

squ

-0.62

teness

-0.61

aaaa

-0.61

POSITIVE LOGITS

Tags

1.14

tags

1.13

 Tags

1.11

uggest

0.87

idy

0.85

ynt

0.85

ynthesis

0.85

 Categories

0.82

 Codec

0.80

ystem

0.79

Activations Density 0.017%

tags or categories listed in a text

references to tags and categorization in the text

No Comments

No Known Activations