INDEX

Explanations

words related to suffocation or suffering

oai_token-act-pair · gpt-3.5-turbo

instances of the word "suff" and its variants, indicating a focus on concepts related to suffering or suffocation

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

 Dragonbound

-0.84

Ô

-0.72

videos

-0.70

 Bravo

-0.69

senal

-0.68

iannopoulos

-0.64

\\\\\\\\

-0.64

\\\\\\\\\\\\\\\\

-0.62

 Noir

-0.62

REDACTED

-0.61

POSITIVE LOGITS

erers

1.26

ocating

1.16

erer

1.12

ocation

1.05

iments

1.02

ocated

0.96

rage

0.95

rag

0.95

ient

0.93

ignt

0.92

Activations Density 0.016%

words related to suffocation or suffering

instances of the word "suff" and its variants, indicating a focus on concepts related to suffering or suffocation

No Comments

No Known Activations