INDEX

Explanations

mentions of blockades

oai_token-act-pair · gpt-3.5-turbo

terms related to blockades and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Sah

-0.76

aum

-0.71

 Bucc

-0.69

Polit

-0.69

itable

-0.67

itar

-0.67

ILLE

-0.67

orah

-0.66

Hart

-0.66

ander

-0.66

POSITIVE LOGITS

 blockade

1.45

 blockers

0.92

 blocker

0.87

 blocking

0.86

wright

0.82

 ramp

0.81

 besie

0.78

 inhibitor

0.77

 barric

0.77

breakers

0.75

Activations Density 0.007%

mentions of blockades

terms related to blockades and their implications

No Comments

No Known Activations