INDEX

Explanations

mentions of "media" in various contexts

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

abad

-0.67

 satirical

-0.66

partisan

-0.64

sung

-0.62

 crooked

-0.60

 Rasmussen

-0.60

 sting

-0.59

-0.58

 phony

-0.58

anks

-0.57

POSITIVE LOGITS

eval

1.07

wiki

0.94

artney

0.80

fire

0.77

 Compos

0.76

 MPEG

0.72

Fire

0.71

player

0.70

enc

0.70

hare

0.68

Activations Density 0.101%

mentions of "media" in various contexts

No Comments

No Known Activations