INDEX

Explanations

expressions referring to something considered standard or characteristic within a specific context

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "typical" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

aska

-0.71

acus

-0.71

nuts

-0.70

hani

-0.68

lands

-0.68

heed

-0.68

hung

-0.67

enced

-0.65

 ashore

-0.64

lean

-0.62

POSITIVE LOGITS

 deviation

0.86

 deviations

0.81

 sized

0.81

 fare

0.78

 weekday

0.76

typ

0.76

ized

0.75

 mammalian

0.75

 attire

0.70

 household

0.70

Activations Density 0.035%

expressions referring to something considered standard or characteristic within a specific context

occurrences of the word "typical" and related variations

No Comments

No Known Activations