INDEX

Explanations

references to validity and existence of information, as well as indications of negation

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

ESSION

-0.73

 cass

-0.71

FUL

-0.70

record

-0.69

intosh

-0.69

anguage

-0.65

terday

-0.65

oice

-0.65

icip

-0.63

caster

-0.63

POSITIVE LOGITS

 dstg

0.76

 ticking

0.63

culated

0.61

 unloaded

0.60

Occup

0.56

 looted

0.56

¥µ

0.56

 reused

0.56

 sourced

0.55

bryce

0.55

Activations Density 0.087%

references to validity and existence of information, as well as indications of negation

No Comments

No Known Activations