INDEX

Explanations

actions or events related to experiences or stories

oai_token-act-pair · gpt-3.5-turbo

references to past experiences and memories

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Digest

-0.70

ãĥĹ

-0.68

 herself

-0.66

Reilly

-0.63

stroke

-0.61

conom

-0.59

arkin

-0.59

FILE

-0.58

 FILE

-0.56

 reper

-0.55

POSITIVE LOGITS

 ourselves

2.21

our

1.39

 ours

1.16

OUR

1.04

Our

1.02

Our

0.94

 together

0.92

we

0.92

 toget

0.87

We

0.86

Activations Density 0.787%

actions or events related to experiences or stories

references to past experiences and memories

No Comments

No Known Activations