INDEX

Explanations

quantitative data and statistical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

دانشنامهٔ

-0.77

mybatisplus

-0.75

horabuena

-0.73

AsUp

-0.70

annica

-0.69

KommentareTeilen

-0.69

amante

-0.68

lanti

-0.66

 ruines

-0.66

[,]

-0.66

POSITIVE LOGITS

0.65

 Morde

0.60

0.59

mathrm

0.57

<eos>

0.56

MathML

0.55

<tr>

0.54

________________

0.53

Activations Density 0.069%

quantitative data and statistical references

No Comments

No Known Activations