INDEX

Explanations

conditional statements indicating consequences

oai_token-act-pair · gpt-3.5-turbo

conditional phrases indicating consequences or alternatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ouched

-0.65

Kit

-0.62

variable

-0.61

ested

-0.60

ovember

-0.60

Written

-0.59

inspired

-0.59

 mindful

-0.58

KER

-0.58

uesday

-0.57

POSITIVE LOGITS

 risk

0.78

 perish

0.76

 collapse

0.72

 else

0.72

 collapses

0.69

aeus

0.68

 demolition

0.67

CHA

0.66

 proceed

0.66

 demol

0.66

Activations Density 0.160%

conditional statements indicating consequences

conditional phrases indicating consequences or alternatives

No Comments

No Known Activations