INDEX

Explanations

phrases introducing a statement or elaboration

oai_token-act-pair · gpt-3.5-turbo

words related to expressions and citations of actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

!.

-0.82

.–

-0.75

.(

-0.72

 unless

-0.72

usercontent

-0.71

$.

-0.71

.''.

-0.70

brance

-0.69

!".

-0.68

POSITIVE LOGITS

BuyableInstoreAndOnline

0.74

 himself

0.70

 herself

0.69

 analogy

0.65

 oneself

0.64

 anonymity

0.61

his

0.60

 hindsight

0.60

 grievances

0.59

 foregoing

0.59

Activations Density 0.518%

phrases introducing a statement or elaboration

words related to expressions and citations of actions or statements

No Comments

No Known Activations