INDEX

Explanations

words related to causing fear or alarm

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "scare" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•layer 2 - fear

No Comments

Negative Logits

cellence

-0.87

ossier

-0.84

empl

-0.83

ioch

-0.77

requisite

-0.76

İĭ

-0.74

uties

-0.74

iciency

-0.74

ophers

-0.72

 composing

-0.71

POSITIVE LOGITS

crow

1.66

mong

1.13

 scare

1.00

 Scare

0.93

ingly

0.81

warts

0.75

 fright

0.73

geon

0.71

 scares

0.69

ulic

0.68

Activations Density 0.007%

words related to causing fear or alarm

occurrences of the word "scare" and its variations

No Comments

No Known Activations