INDEX

Explanations

the name "Ko" in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Ko" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Interstitial

-0.87

ãĤ¼ãĤ¦ãĤ¹

-0.75

 iPads

-0.75

ACTED

-0.74

 Creed

-0.74

ãĥ´ãĤ¡

-0.73

HCR

-0.71

CPC

-0.71

STATE

-0.69

aneous

-0.68

POSITIVE LOGITS

zzi

1.11

Å¡

1.04

ono

0.98

osta

0.97

jo

0.96

ji

0.94

Ko

0.92

eta

0.91

zy

0.90

Äį

0.88

Activations Density 0.007%

the name "Ko" in various contexts

mentions of the name "Ko" and its variations in context

No Comments

No Known Activations