INDEX

Explanations

code snippets and programming-related terms

oai_token-act-pair · gpt-3.5-turbo

coding elements and programming terminology

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

 Chance

-0.79

 Friendship

-0.76

 Charity

-0.76

 Concent

-0.75

 Weeks

-0.75

 Gron

-0.75

 MacArthur

-0.75

ANG

-0.75

ãĥ¯ãĥ³

-0.74

 Therapy

-0.73

POSITIVE LOGITS

args

1.04

rc

0.98

ql

0.98

plugin

0.97

utils

0.96

ctl

0.96

cd

0.95

pd

0.94

0.93

info

0.91

Activations Density 0.182%

code snippets and programming-related terms

coding elements and programming terminology

No Comments

No Known Activations