INDEX

Explanations

phrases starting with "Never" where "Never" is followed by a specific action or description

oai_token-act-pair · gpt-3.5-turbo

the repeated phrase "Never" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

eers

-0.71

redients

-0.71

otle

-0.67

ipation

-0.65

uliffe

-0.65

hoe

-0.65

 Jindal

-0.64

allery

-0.63

virt

-0.63

uers

-0.62

POSITIVE LOGITS

theless

1.63

winter

0.93

mind

0.86

entimes

0.82

 hesitate

0.81

 EVER

0.77

 ceases

0.76

 Alone

0.71

thing

0.71

 Forget

0.70

Activations Density 0.030%

phrases starting with "Never" where "Never" is followed by a specific action or description

the repeated phrase "Never" in various contexts

No Comments

No Known Activations