INDEX

Explanations

terms related to work, preparation, and decision-making

oai_token-act-pair · gpt-3.5-turbo

phrases related to preparation and efforts toward objectives

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

illegal

-0.72

misc

-0.71

aven

-0.70

vol

-0.68

 exception

-0.67

except

-0.66

laughs

-0.66

dra

-0.65

monkey

-0.65

cpp

-0.63

POSITIVE LOGITS

 prepares

0.85

 progresses

0.85

 unfolds

0.84

 consolid

0.79

 transitioned

0.72

 increasingly

0.72

 progressed

0.71

PTS

0.71

 Hilbert

0.71

 progressively

0.70

Activations Density 0.286%

terms related to work, preparation, and decision-making

phrases related to preparation and efforts toward objectives

No Comments

No Known Activations