INDEX

Explanations

words related to negative connotations, especially those that involve demeaning actions or words

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "dem" 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 @ 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

 supper

-0.71

URN

-0.67

WAYS

-0.66

FORE

-0.66

 Nightmares

-0.64

 endless

-0.61

TERN

-0.61

waters

-0.61

cano

-0.61

 blasphemy

-0.60

POSITIVE LOGITS

otion

1.21

otions

1.13

agogue

1.13

agog

1.12

aterial

1.10

ographically

1.10

igration

1.09

ilit

1.08

obil

1.07

ean

1.03

Activations Density 0.011%

words related to negative connotations, especially those that involve demeaning actions or words

mentions of the word "dem" in various contexts

No Comments

No Known Activations