INDEX

Explanations

words related to names, titles, or designations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.82

 readiness

-0.70

²¾

-0.66

 chains

-0.62

 envy

-0.61

 bang

-0.60

xus

-0.58

¥µ

-0.58

 backlog

-0.58

 craving

-0.58

POSITIVE LOGITS

é¾įå

0.85

ruary

0.84

luster

0.80

ilial

0.77

ilon

0.74

illet

0.73

agy

0.73

reau

0.70

emale

0.69

cia

0.69

Activations Density 0.027%

words related to names, titles, or designations

No Comments

No Known Activations