INDEX

Explanations

sentences with words related to causing fear or deception

oai_token-act-pair · gpt-3.5-turbo

references to public sentiments or perceptions influenced by fear-mongering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

played

-0.62

 documented

-0.57

 consulting

-0.57

 confirmed

-0.56

 ital

-0.54

 roundup

-0.54

 spelled

-0.53

tackle

-0.53

CLASSIFIED

-0.53

 occupation

-0.53

POSITIVE LOGITS

 into

0.97

into

0.92

 Into

0.80

allo

0.75

 gull

0.75

selves

0.72

ritical

0.72

 minds

0.70

uces

0.69

iets

0.68

Activations Density 0.359%

sentences with words related to causing fear or deception

references to public sentiments or perceptions influenced by fear-mongering

No Comments

No Known Activations