INDEX

Explanations

verbs related to legal processes or actions

oai_token-act-pair · gpt-3.5-turbo

terms related to negotiation and legal proceedings

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

ulner

-0.69

ilers

-0.62

switch

-0.62

ortium

-0.62

eco

-0.62

iris

-0.61

amy

-0.59

hitting

-0.59

eele

-0.57

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.57

POSITIVE LOGITS

urally

0.77

ially

0.76

zzle

0.67

LY

0.64

 against

0.64

NESS

0.64

 advising

0.63

OTUS

0.63

ly

0.63

enance

0.62

Activations Density 0.149%

verbs related to legal processes or actions

terms related to negotiation and legal proceedings

No Comments

No Known Activations