INDEX

Explanations

Code snippets

np_max-act · gemini-2.0-flash

tokens that are keys/field names in structured data (e.g., config/json/metadata fields like "autoupdate" or "result").

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

New Auto-Interp

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

licas

-0.08

 owners

-0.07

plier

-0.07

api

-0.07

.dumps

-0.07

null

-0.07

$user

-0.07

.defaultValue

-0.07

	Rect

-0.07

	iter

-0.07

POSITIVE LOGITS

 Horde

0.09

Выб

0.09

_Se

0.09

猇

0.09

_QU

0.09

_Ph

0.09

gob

0.08

검

0.08

И

0.08

 Ком

0.08

Activations Density 1.799%

Code snippets

tokens that are keys/field names in structured data (e.g., config/json/metadata fields like "autoupdate" or "result").

No Comments

No Known Activations

Code snippets

tokens that are keys/field names in structured data (e.g., config/json/metadata fields like "autoupdate" or "result").

No Comments

No Known Activations