INDEX

Explanations

reflexive pronouns followed by verbs indicating action

oai_token-act-pair · gpt-3.5-turbo

references to the second person pronoun "you."

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

blem

-0.77

 âĵĺ

-0.75

oval

-0.72

emen

-0.69

gob

-0.68

istries

-0.67

punk

-0.66

 Ambro

-0.66

DOM

-0.65

existence

-0.64

POSITIVE LOGITS

 progresses

0.69

 desc

0.65

 prepares

0.65

 crow

0.65

iris

0.64

sun

0.62

phr

0.61

 critic

0.61

 pointed

0.60

 empt

0.60

Activations Density 0.113%

reflexive pronouns followed by verbs indicating action

references to the second person pronoun "you."

No Comments

No Known Activations