INDEX

Explanations

phrases related to specific incidents or events happening in various locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "happened" in various contexts of events or incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

tan

-0.94

igration

-0.86

bern

-0.80

ocyte

-0.79

tin

-0.76

ocytes

-0.74

ãģĹ

-0.74

ularity

-0.73

hee

-0.73

vernment

-0.72

POSITIVE LOGITS

 yesterday

0.84

 shortly

0.81

 catast

0.80

 earlier

0.78

 downstairs

0.78

 during

0.75

 abruptly

0.74

 coinc

0.73

 tragically

0.73

 accidentally

0.72

Activations Density 0.076%

phrases related to specific incidents or events happening in various locations

occurrences of the word "happened" in various contexts of events or incidents

No Comments

No Known Activations