INDEX

Explanations

terms related to glossiness and related phenomena in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cffffcc

-0.84

ourke

-0.77

Interstitial

-0.73

berus

-0.73

âĹ¼

-0.69

 externalToEVAOnly

-0.68

======

-0.68

å§

-0.67

gd

-0.64

RON

-0.63

POSITIVE LOGITS

iness

1.12

ary

1.10

es

1.03

efully

1.02

ier

0.99

aries

0.97

ophon

0.94

iest

0.90

 gloss

0.90

entimes

0.86

Activations Density 0.003%

terms related to glossiness and related phenomena in various contexts

No Comments

No Known Activations