INDEX

Explanations

technical terms related to software or system environments

oai_token-act-pair · gpt-3.5-turbo

references to various types of environments, particularly in software or technical contexts

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

headed

-0.92

sonian

-0.91

heading

-0.90

thood

-0.89

doms

-0.88

head

-0.86

der

-0.84

mad

-0.83

uster

-0.80

awar

-0.80

POSITIVE LOGITS

 environments

0.95

 environment

0.95

 variables

0.89

 conducive

0.85

 Environment

0.83

 variable

0.80

 conditions

0.79

Variable

0.78

 atmosp

0.74

eers

0.73

Activations Density 0.036%

technical terms related to software or system environments

references to various types of environments, particularly in software or technical contexts

No Comments

No Known Activations