INDEX

Explanations

nouns related to physical objects or materials

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and their usage 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

½

-0.72

tera

-0.67

ļ

-0.67

ENCY

-0.66

endo

-0.64

mite

-0.64

 Dynasty

-0.62

ibl

-0.62

 Anniversary

-0.60

cend

-0.60

POSITIVE LOGITS

 thereby

1.34

 hoping

1.14

 prompting

1.09

 resulting

1.08

 respectively

1.07

 intending

1.05

 allowing

1.04

 causing

1.00

 ensuring

1.00

mim

0.98

Activations Density 0.409%

nouns related to physical objects or materials

punctuation marks and their usage in various contexts

No Comments

No Known Activations