INDEX

Explanations

the word "Sha" in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific person or entity named "Sha."

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

dit

-0.80

ATOR

-0.74

ENTS

-0.73

sburgh

-0.72

 McCann

-0.68

geist

-0.68

ships

-0.67

tions

-0.67

 Dayton

-0.66

gence

-0.66

POSITIVE LOGITS

olin

1.09

ikh

1.01

isha

0.97

Sha

0.97

osh

0.96

pered

0.93

qi

0.89

pling

0.85

oche

0.84

qua

0.82

Activations Density 0.006%

the word "Sha" in various contexts

mentions of a specific person or entity named "Sha."

No Comments

No Known Activations