INDEX

Explanations

situations where a decision is being reversed

oai_token-act-pair · gpt-3.5-turbo

instances of the word "reversed" and its variations in various contexts

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

lished

-0.88

chens

-0.79

Interstitial

-0.77

akening

-0.73

chen

-0.72

ogi

-0.72

league

-0.68

OULD

-0.67

bags

-0.67

ivities

-0.66

POSITIVE LOGITS

 revers

0.95

 reversal

0.87

 reversed

0.81

 chronological

0.81

 reversing

0.73

CLASSIFIED

0.70

 swipe

0.69

 handshake

0.65

 Genie

0.65

ward

0.65

Activations Density 0.016%

situations where a decision is being reversed

instances of the word "reversed" and its variations in various contexts

No Comments

No Known Activations