INDEX

Explanations

terms related to organized activities or missions

oai_token-act-pair · gpt-3.5-turbo

words related to conditions, particularly in the context of actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãĤ¨ãĥ«

-0.70

ashington

-0.65

CLOSE

-0.65

psc

-0.65

JP

-0.64

Effective

-0.63

twitter

-0.62

Neg

-0.62

Interstitial

-0.61

WR

-0.61

POSITIVE LOGITS

itions

1.56

ition

1.13

itious

0.98

chool

0.95

naire

0.93

uits

0.93

hower

0.89

naires

0.88

eries

0.87

omething

0.86

Activations Density 0.006%

terms related to organized activities or missions

words related to conditions, particularly in the context of actions or states

No Comments

No Known Activations