INDEX

Explanations

negative sentiment or expressions of discontent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.3.hook_attn_out

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mine

-0.79

 sake

-0.74

 hires

-0.67

 machinery

-0.66

 hire

-0.66

 appliances

-0.66

urities

-0.66

 substitutes

-0.65

 liability

-0.65

 construction

-0.64

POSITIVE LOGITS

adelphia

0.99

grave

0.81

Hai

0.75

vati

0.75

CVE

0.73

Bang

0.72

JM

0.68

bryce

0.67

yip

0.66

Sov

0.66

Activations Density 0.064%

negative sentiment or expressions of discontent

No Comments

No Known Activations