INDEX

Explanations

questions and conversational prompts

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

review positive statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sizeCache

-0.72

principalTable

-0.69

AddTagHelper

-0.65

WriteBarrier

-0.64

pushFollow

-0.61

 AssemblyProduct

-0.59

webElementGuid

-0.57

InitVars

-0.56

EDEFAULT

-0.56

RTSC

-0.56

POSITIVE LOGITS

 comment

0.48

 positives

0.48

 POSITIVE

0.47

 praise

0.46

 review

0.44

Positive

0.43

 positif

0.43

 positive

0.43

 thumbs

0.43

Overall

0.42

Activations Density 0.082%

questions and conversational prompts

review positive statements

No Comments

No Known Activations