INDEX

Explanations

code snippets containing specific programming functions or methods

oai_token-act-pair · gpt-3.5-turbo

parentheses and associated structures commonly found in code or mathematical expressions

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

ylum

-0.81

entimes

-0.70

 eyel

-0.70

 handc

-0.69

 grap

-0.68

 ransom

-0.67

 electr

-0.67

 wart

-0.67

âĢĳ

-0.66

 incarn

-0.66

POSITIVE LOGITS

username

0.94

default

0.93

...)

0.89

src

0.88

())

0.88

current

0.87

actual

0.86

verb

0.85

input

0.84

shown

0.83

Activations Density 0.029%

code snippets containing specific programming functions or methods

parentheses and associated structures commonly found in code or mathematical expressions

No Comments

No Known Activations