INDEX

Explanations

references to heavily armed police units like SWAT teams

oai_token-act-pair · gpt-3.5-turbo

terms related to SWAT teams and military presence in law enforcement

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

criptions

-0.80

Rate

-0.75

 DRAG

-0.75

ranged

-0.71

ð

-0.71

yt

-0.69

hare

-0.69

eas

-0.67

iard

-0.66

lected

-0.66

POSITIVE LOGITS

ilitary

0.92

 militar

0.87

 standoff

0.85

 SWAT

0.80

ormal

0.79

intendent

0.79

 LAPD

0.76

 SEAL

0.75

Ops

0.72

 Officers

0.71

Activations Density 0.082%

references to heavily armed police units like SWAT teams

terms related to SWAT teams and military presence in law enforcement

No Comments

No Known Activations