INDEX

Explanations

references to the concept of perception, particularly in relation to experiences and sensory information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

RenderAtEndOf

-0.86

ftagPool

-0.72

tvguidetime

-0.70

SPATH

-0.70

]--;

-0.66

 Shreve

-0.64

 Bourgoin

-0.62

Smarty

-0.61

RegressionTest

-0.59

ⓧ

-0.59

POSITIVE LOGITS

 impression

0.70

eq

0.70

EQ

0.65

eq

0.61

 <=",

0.61

InjectMocks

0.61

 perception

0.60

EQ

0.58

impression

0.57

Eq

0.56

Activations Density 0.159%

references to the concept of perception, particularly in relation to experiences and sensory information

No Comments

No Known Activations