INDEX

Explanations

adjectives or verbs related to ethical judgment

oai_token-act-pair · gpt-3.5-turbo

expressions of strong opinions or judgments about individuals' actions or character

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

selves

-0.68

mination

-0.64

 Composite

-0.60

 Mages

-0.57

 guiActiveUnfocused

-0.56

 unison

-0.56

 Colleges

-0.55

VERTISEMENT

-0.54

eps

-0.54

 Collective

-0.54

POSITIVE LOGITS

 himself

1.17

 Himself

0.71

ãģ®é

0.68

 personally

0.67

 subordinates

0.62

panic

0.62

 wife

0.58

 girlfriend

0.56

liest

0.56

 directing

0.55

Activations Density 1.540%

adjectives or verbs related to ethical judgment

expressions of strong opinions or judgments about individuals' actions or character

No Comments

No Known Activations