INDEX

Explanations

references to different types of habits or behaviors, such as driving habits, eating patterns, and purchasing behavior

oai_token-act-pair · gpt-3.5-turbo

terms related to habits and behaviors

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

£ı

-0.78

IRC

-0.77

ignant

-0.73

Slot

-0.69

CAST

-0.68

lit

-0.68

vous

-0.67

Lens

-0.66

ãĥ©ãĥ³

-0.64

ropolis

-0.64

POSITIVE LOGITS

 continuum

0.78

quo

0.77

changes

0.77

 mismatch

0.76

 indicator

0.73

 correlates

0.73

 index

0.71

 varies

0.71

 Index

0.70

heres

0.70

Activations Density 0.309%

references to different types of habits or behaviors, such as driving habits, eating patterns, and purchasing behavior

terms related to habits and behaviors

No Comments

No Known Activations