INDEX

Explanations

phrases related to negative outcomes or repercussions

oai_token-act-pair · gpt-3.5-turbo

phrases that discuss the consequences of actions or events

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

uni

-0.73

bor

-0.73

ymph

-0.72

estine

-0.70

yne

-0.68

este

-0.68

Gun

-0.68

estone

-0.67

BN

-0.67

estones

-0.67

POSITIVE LOGITS

 consequences

1.10

 repercussions

0.89

 fallout

0.86

 consequence

0.84

 havoc

0.82

 ramifications

0.80

 thereof

0.78

romeda

0.76

 disobedience

0.76

 reperc

0.76

Activations Density 0.018%

phrases related to negative outcomes or repercussions

phrases that discuss the consequences of actions or events

No Comments

No Known Activations