INDEX

Explanations

specific symbols or characters within the text

oai_token-act-pair · gpt-3.5-turbo

occurrences of colons and other punctuation marks related to narrative structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 uranium

-0.85

 synerg

-0.85

 payroll

-0.77

¥ŀ

-0.75

neb

-0.75

iod

-0.74

 centralized

-0.71

 techn

-0.71

 neut

-0.70

rye

-0.69

POSITIVE LOGITS

Scroll

1.82

VIDEO

1.36

Pict

1.35

HOW

1.31

SHARE

1.30

':

1.28

Speaking

1.28

WHAT

1.27

',

1.25

Activations Density 0.096%

specific symbols or characters within the text

occurrences of colons and other punctuation marks related to narrative structure

No Comments

No Known Activations