INDEX

Explanations

programming-related elements such as method calls and object attributes

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

Code snippets using "this" or "obj"

np_acts-logits-general · gemini-2.0-flash

this in code

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Elsewhere

-0.55

 برانيه

-0.51

 đàn

-0.49

ليق

-0.46

jao

-0.45

 TestBed

-0.44

ดาว

-0.43

qtype

-0.43

 Seem

-0.43

ể

-0.43

POSITIVE LOGITS

::

0.90

>::

0.69

########.

0.67

::$

0.65

::

0.64

 فريبيس

0.64

oa̍t

0.60

 hảo

0.57

'])->

0.57

conscious

0.55

Activations Density 0.097%

programming-related elements such as method calls and object attributes

Code snippets using "this" or "obj"

this in code

No Comments

No Known Activations