INDEX

Explanations

instances of permission or allowance in various contexts

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

"allow" or "allows"

np_acts-logits-general · gemini-2.0-flash

allowing access

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

 CreateTagHelper

-0.88

AndEndTag

-0.81

SequentialGroup

-0.78

 كومونز

-0.78

LookAnd

-0.74

 AssemblyCompany

-0.72

IsContent

-0.71

@[+][

-0.71

numerusform

-0.71

 références

-0.70

POSITIVE LOGITS

 access

0.86

ALLOW

0.82

 ALLOW

0.76

 permits

0.76

 Allows

0.72

ances

0.69

 Allow

0.69

 allows

0.69

access

0.68

Allows

0.67

Activations Density 0.121%

instances of permission or allowance in various contexts

"allow" or "allows"

allowing access

No Comments

No Known Activations