INDEX

Explanations

words related to legal language or terms

oai_token-act-pair · gpt-3.5-turbo

terms related to exemptions and comparisons across different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 thanking

-0.70

 flanked

-0.62

 thanked

-0.59

amo

-0.54

 --------------------------------

-0.54

CHAT

-0.54

 promptly

-0.54

``

-0.53

↵Âł

-0.53

 preferably

-0.52

POSITIVE LOGITS

 counterparts

0.81

 predecessors

0.70

nor

0.69

 equivalents

0.69

 ones

0.67

 anymore

0.64

 predec

0.62

 attRot

0.62

 altogether

0.61

 peers

0.60

Activations Density 0.798%

words related to legal language or terms

terms related to exemptions and comparisons across different contexts

No Comments

No Known Activations