INDEX

Explanations

descriptions of violent events involving victims being harmed or injured

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "was" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Countries

-0.81

isites

-0.78

 Extend

-0.78

 Requirements

-0.73

isite

-0.73

 Critics

-0.72

 Costs

-0.71

 Taxes

-0.68

inav

-0.68

 aspire

-0.67

POSITIVE LOGITS

 hospitalized

1.35

 stabbed

1.19

 arrested

1.16

 transported

1.15

 assaulted

1.14

 asleep

1.12

 fatally

1.12

 evacuated

1.11

 bitten

1.09

 killed

1.07

Activations Density 0.134%

descriptions of violent events involving victims being harmed or injured

instances of the verb "was" and its variations in different contexts

No Comments

No Known Activations