INDEX

Explanations

references to legal matters or lawsuits

oai_token-act-pair · gpt-3.5-turbo

references to legal actions or lawsuits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atomic

-0.83

odes

-0.82

eele

-0.82

combe

-0.80

olls

-0.75

erd

-0.73

oyal

-0.72

obyl

-0.72

ode

-0.71

ordinate

-0.68

POSITIVE LOGITS

 filed

0.96

 alleging

0.92

 against

0.91

 alleges

0.90

suit

0.85

 lawsuit

0.81

suits

0.81

 suing

0.79

 settlement

0.77

 accusing

0.75

Activations Density 0.022%

references to legal matters or lawsuits

references to legal actions or lawsuits

No Comments

No Known Activations