INDEX

Explanations

phrases related to evaluating or critiquing something

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of holding something up or supporting it, both literally and metaphorically

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enfranch

-0.72

kHz

-0.69

Depth

-0.68

cest

-0.66

kHz

-0.65

ceivable

-0.64

 Lauder

-0.63

ascus

-0.62

cham

-0.61

 Racing

-0.60

POSITIVE LOGITS

river

0.79

rights

0.70

rawl

0.68

olicy

0.68

 barriers

0.66

inar

0.66

 walls

0.65

 similarities

0.65

adesh

0.65

 positives

0.64

Activations Density 0.027%

phrases related to evaluating or critiquing something

phrases related to the concept of holding something up or supporting it, both literally and metaphorically

No Comments

No Known Activations