INDEX

Explanations

proper nouns related to a specific entity named Henderson

oai_token-act-pair · gpt-3.5-turbo

the name "Henderson" used in various contexts and descriptions

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

onomy

-0.69

-0.68

opsy

-0.68

EP

-0.68

grading

-0.65

tale

-0.63

cing

-0.63

urity

-0.62

ebra

-0.62

apping

-0.61

POSITIVE LOGITS

 Henderson

1.08

ragon

0.89

ville

0.83

forth

0.79

ega

0.76

eming

0.72

agne

0.71

wich

0.71

 Alvarez

0.69

lers

0.68

Activations Density 0.026%

proper nouns related to a specific entity named Henderson

the name "Henderson" used in various contexts and descriptions

No Comments

No Known Activations