INDEX

Explanations

verbs or adjectives related to discouragement or prevention

oai_token-act-pair · gpt-3.5-turbo

words related to discouragement or dissuasion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Not in Any Lists

No Comments

Negative Logits

ophon

-0.87

imony

-0.82

ammy

-0.80

odore

-0.78

ebus

-0.77

opus

-0.74

rieg

-0.72

eus

-0.71

oop

-0.69

oÄŁ

-0.69

POSITIVE LOGITS

 discour

0.87

asive

0.74

 dissu

0.73

avorite

0.72

 discouraging

0.71

////

0.69

 batted

0.68

 discouraged

0.68

 inhib

0.66

GGGGGGGG

0.66

Activations Density 0.030%

verbs or adjectives related to discouragement or prevention

words related to discouragement or dissuasion

No Comments

No Known Activations