INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

verbs indicating existence or presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ank

-0.79

imar

-0.71

isman

-0.68

 exceeds

-0.68

author

-0.66

wake

-0.65

 belie

-0.65

 hadn

-0.65

 avoids

-0.64

Author

-0.64

POSITIVE LOGITS

GROUND

0.72

ãĥ¼ãĥ³

0.69

 Remy

0.68

ãĤĮ

0.65

tnc

0.65

FTWARE

0.64

 Sanct

0.64

 gaping

0.64

 ominous

0.62

 beaut

0.61

Activations Density 0.423%

proper nouns

verbs indicating existence or presence

No Comments

No Known Activations