INDEX

Explanations

phrases indicating predictions, assessments, or calculations about various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res_post_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.10.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

actionDate

-0.85

NetMessage

-0.77

£ı

-0.77

maxwell

-0.77

yrim

-0.76

ciating

-0.74

Nir

-0.73

PAT

-0.73

Dar

-0.71

 Levine

-0.71

POSITIVE LOGITS

Bo

1.73

Mo

1.70

Mo

1.69

Ro

1.68

Ro

1.68

Bo

1.59

Ho

1.57

Ho

1.57

Lo

1.54

Fo

1.52

Activations Density 6.356%

phrases indicating predictions, assessments, or calculations about various contexts

No Comments

No Known Activations