INDEX

Explanations

negative connotations or implications in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

tvguidetime

-0.69

umbu

-0.64

($('#

-0.61

($("#

-0.59

iedler

-0.59

 FileInputStream

-0.59

 незавершена

-0.58

ance

-0.58

 academic

-0.57

{{$

-0.57

POSITIVE LOGITS

msgSender

0.74

RenderAtEndOf

0.68

 Administrativna

0.62

msgTypes

0.60

verwijspagina

0.60

↵↵

0.59

 SwitchCompat

0.56

 بيها

0.55

StoryboardSegue

0.54

Facades

0.53

Activations Density 0.029%

negative connotations or implications in statements

No Comments

No Known Activations