INDEX

Explanations

phrases related to a specific keyword or action, which is the word "Pass."

oai_token-act-pair · gpt-3.5-turbo

references to "Pass" in various contexts, possibly indicating a specific term or concept in a given subject matter

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

imus

-0.85

onies

-0.73

oric

-0.72

ragon

-0.68

 moderator

-0.68

lessly

-0.65

eryl

-0.65

alysed

-0.63

odynam

-0.61

amy

-0.61

POSITIVE LOGITS

 Pass

4.04

Pass

2.68

pass

2.12

 PASS

2.03

 pass

2.00

 passes

1.75

PASS

1.63

 Passing

1.58

 Passage

1.54

 passing

1.21

Activations Density 0.015%

phrases related to a specific keyword or action, which is the word "Pass."

references to "Pass" in various contexts, possibly indicating a specific term or concept in a given subject matter

No Comments

No Known Activations