INDEX

Explanations

statements and claims related to reports or official communications

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

GW

-0.71

 runway

-0.68

 guiActiveUnfocused

-0.67

 doorstep

-0.65

Enabled

-0.64

DERR

-0.63

 whichever

-0.63

Quantity

-0.63

usterity

-0.61

Disclaimer

-0.61

POSITIVE LOGITS

ept

0.71

andro

0.70

enf

0.70

bably

0.69

opa

0.67

rb

0.66

tailed

0.66

bara

0.64

incial

0.63

querque

0.63

Activations Density 0.736%

statements and claims related to reports or official communications

No Comments

No Known Activations