INDEX

Explanations

legal and investigative terms

oai_token-act-pair · gpt-3.5-turbo

terms related to legal actions and investigations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sacrific

-0.71

agog

-0.67

 Rebell

-0.63

 Decay

-0.63

 negatives

-0.61

 undes

-0.58

 Views

-0.58

apest

-0.54

natureconservancy

-0.54

 newcomers

-0.54

POSITIVE LOGITS

 against

0.82

 regarding

0.81

 relating

0.79

 aimed

0.77

 Wednesday

0.75

 prohibiting

0.75

 Thursday

0.75

 targeting

0.74

 Monday

0.74

 citing

0.73

Activations Density 0.307%

legal and investigative terms

terms related to legal actions and investigations

No Comments

No Known Activations