INDEX

Explanations

mentions of scare tactics

oai_token-act-pair · gpt-3.5-turbo

instances of the word "scare" and its variations relating to fear or intimidation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

cellence

-0.90

empl

-0.85

ioch

-0.74

requisite

-0.74

processing

-0.74

 offic

-0.73

actions

-0.73

 composing

-0.72

 Merge

-0.72

eous

-0.71

POSITIVE LOGITS

crow

1.54

 scare

1.23

mong

1.04

 Scare

1.01

 scares

0.82

 fright

0.82

warts

0.78

inventoryQuantity

0.77

escape

0.77

borough

0.73

Activations Density 0.005%

mentions of scare tactics

instances of the word "scare" and its variations relating to fear or intimidation

No Comments

No Known Activations