INDEX

Explanations

mentions of the name "Ko"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the sequence "ko" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

glass

-0.83

 glim

-0.82

Ö¼

-0.81

spread

-0.74

grounds

-0.73

ienced

-0.72

icist

-0.70

 narrator

-0.70

Ü

-0.69

itud

-0.68

POSITIVE LOGITS

zzi

1.24

ppa

1.06

zzo

0.99

pps

0.96

pper

0.95

ichi

0.91

opa

0.90

ppy

0.89

verage

0.89

ek

0.88

Activations Density 0.012%

mentions of the name "Ko"

occurrences of the sequence "ko" in various contexts

No Comments

No Known Activations