INDEX

Explanations

phrases related to actions or tasks being accomplished

oai_token-act-pair · gpt-3.5-turbo

expressions of communal activity and collaboration

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

ONSORED

-0.65

Attach

-0.59

ISION

-0.58

 circumstances

-0.56

 Accountability

-0.56

 Integrity

-0.56

 Justice

-0.55

ãĥĦ

-0.55

 Audit

-0.54

 reforms

-0.54

POSITIVE LOGITS

joice

0.71

wolves

0.68

unts

0.67

their

0.65

tumblr

0.62

animate

0.62

ometimes

0.62

they

0.62

 cones

0.61

common

0.60

Activations Density 1.890%

phrases related to actions or tasks being accomplished

expressions of communal activity and collaboration

No Comments

No Known Activations