INDEX

Explanations

phrases related to loss or negative outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of loss and its consequences

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

Catalog

-0.77

eller

-0.71

à¼

-0.70

ulhu

-0.69

nis

-0.67

Ask

-0.67

had

-0.67

wcsstore

-0.67

çīĪ

-0.67

hoe

-0.65

POSITIVE LOGITS

 limbs

0.91

 consciousness

0.90

 virginity

0.87

 innocence

0.85

luster

0.78

 limb

0.77

 momentum

0.76

 liberty

0.75

 oxygen

0.75

 electrons

0.74

Activations Density 0.077%

phrases related to loss or negative outcomes

phrases related to the concept of loss and its consequences

No Comments

No Known Activations