INDEX

Explanations

unnamed or unspecified things mentioned earlier in the text

oai_token-act-pair · gpt-3.5-turbo

references to previously mentioned concepts or items

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

ples

-0.71

©¶æ

-0.65

 advisers

-0.63

 Observer

-0.61

izable

-0.59

 bindings

-0.58

agent

-0.58

 interval

-0.58

iments

-0.58

 psychiatrists

-0.58

POSITIVE LOGITS

ãĤ¤ãĥĪ

0.83

STEM

0.80

ãĥ´ãĤ¡

0.77

ãĤ»

0.68

BSD

0.67

ï¸ı

0.67

BuyableInstoreAndOnline

0.66

çľ

0.65

Marginal

0.63

ãĥ¼ãĥĨãĤ£

0.63

Activations Density 0.116%

unnamed or unspecified things mentioned earlier in the text

references to previously mentioned concepts or items

No Comments

No Known Activations