INDEX

Explanations

references to additional details or explanations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_post_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 effected

-0.71

edo

-0.69

 lasted

-0.66

 thanking

-0.65

icial

-0.64

mouth

-0.64

 behaved

-0.62

 centered

-0.62

 inbox

-0.61

 appealed

-0.61

POSITIVE LOGITS

}}}

0.82

 Â¶

0.78

 Figures

0.71

 Protocol

0.67

idable

0.67

WAYS

0.65

lance

0.65

Nation

0.63

Sok

0.63

 detail

0.62

Activations Density 0.605%

references to additional details or explanations within the text

No Comments

No Known Activations

references to additional details or explanations within the text

No Comments

No Known Activations