INDEX

Explanations

phrases related to dropping out of situations or activities

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

geries

-0.69

WT

-0.67

DEBUG

-0.64

PROV

-0.60

EY

-0.59

yth

-0.59

alid

-0.59

OIL

-0.58

Fo

-0.57

shaw

-0.57

POSITIVE LOGITS

lier

0.79

ta

0.75

quished

0.72

 altogether

0.71

owship

0.71

due

0.71

bart

0.70

paced

0.70

 amid

0.69

fitting

0.69

Activations Density 0.011%

phrases related to dropping out of situations or activities

No Comments

No Known Activations