INDEX

Explanations

terms related to standardization or uniformity

oai_token-act-pair · gpt-3.5-turbo

terms related to standardized systems and unification in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

=-=-=-=-=-=-=-=-

-0.91

thur

-0.82

deals

-0.81

=-=-=-=-

-0.78

ertodd

-0.76

Khe

-0.75

idian

-0.73

thus

-0.72

dain

-0.72

ionage

-0.71

POSITIVE LOGITS

 phased

0.91

 standardized

0.91

nesday

0.82

 unified

0.77

 shorth

0.74

 cheating

0.73

urally

0.72

iated

0.72

ocument

0.72

 testing

0.71

Activations Density 0.020%

terms related to standardization or uniformity

terms related to standardized systems and unification in various contexts

No Comments

No Known Activations