INDEX

Explanations

the word "Ham" either with a specific numerical value or with a high activation, and contextually may be associated with multiple different mentions of "Ham" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to the character Hamlet from Shakespeare's play

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

uality

-0.80

CLASSIFIED

-0.67

ãģį

-0.65

igslist

-0.64

ç«

-0.64

ãĥ´

-0.63

terday

-0.62

Downloadha

-0.62

 Leone

-0.62

ahead

-0.61

POSITIVE LOGITS

mers

1.24

elin

1.13

pton

1.12

ster

1.06

ilton

1.05

strings

1.04

sterdam

1.01

mer

0.99

rod

0.94

monds

0.94

Activations Density 0.011%

the word "Ham" either with a specific numerical value or with a high activation, and contextually may be associated with multiple different mentions of "Ham" in various contexts

references to the character Hamlet from Shakespeare's play

No Comments

No Known Activations