INDEX

Explanations

variables or programming terms and issues

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "variable" and its variations in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

llah

-0.81

ï¸

-0.80

furt

-0.80

İ

-0.79

ļé

-0.79

Ĥª

-0.78

lez

-0.76

Ķ

-0.75

letters

-0.75

¿½

-0.75

POSITIVE LOGITS

variable

0.87

 variables

0.82

 variable

0.76

ially

0.74

wine

0.74

staking

0.73

 resistor

0.71

izations

0.70

 Bind

0.70

 Variable

0.70

Activations Density 0.027%

variables or programming terms and issues

occurrences of the word "variable" and its variations in a programming context

No Comments

No Known Activations