INDEX

Explanations

function calls that display messages or alerts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

IsPostBack

-0.84

extAlignment

-0.84

AdapterView

-0.81

Rujuakan

-0.75

brainly

-0.72

featureID

-0.71

 CreateTagHelper

-0.69

initComponents

-0.67

发表于

-0.66

VolleyError

-0.66

POSITIVE LOGITS

multicolumn

3.17

multirow

1.52

matchCondition

0.72

makeText

0.61

 MyBatis

0.60

ɵɵ

0.60

ViewFeatures

0.58

 colspan

0.58

texttt

0.56

tē

0.56

Activations Density 0.014%

function calls that display messages or alerts

No Comments

No Known Activations