INDEX

Explanations

phrases related to providing detailed instructions or analysis on a step-by-step basis

oai_token-act-pair · gpt-3.5-turbo

step-related instructions and guidelines

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gart

-0.73

ktop

-0.73

Sensor

-0.71

forts

-0.70

pots

-0.68

dor

-0.68

iov

-0.67

ibaba

-0.66

irk

-0.66

esta

-0.64

POSITIVE LOGITS

 bilingual

0.76

fac

0.74

 rebutt

0.72

 basis

0.72

 manic

0.70

 instructions

0.67

amorph

0.67

 outline

0.66

 correspondence

0.66

 comparisons

0.65

Activations Density 0.063%

phrases related to providing detailed instructions or analysis on a step-by-step basis

step-related instructions and guidelines

No Comments

No Known Activations