INDEX

Explanations

instances where performance is mentioned, particularly in the context of reviews, evaluations, or achievements

oai_token-act-pair · gpt-3.5-turbo

terms related to performance and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Adds

-0.68

uminati

-0.66

ROR

-0.65

abbit

-0.64

 Objects

-0.63

llah

-0.63

Nig

-0.61

gur

-0.59

ipal

-0.58

MIT

-0.58

POSITIVE LOGITS

 against

0.95

 offensively

0.94

 defensively

0.93

 performances

0.92

 last

0.84

 streak

0.82

 thus

0.80

 lately

0.79

 showcasing

0.79

 notwithstanding

0.79

Activations Density 0.198%

instances where performance is mentioned, particularly in the context of reviews, evaluations, or achievements

terms related to performance and evaluations

No Comments

No Known Activations