INDEX

Explanations

names or terms related to labels or classifications

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "abel" and variations of it in different 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

usalem

-0.82

awar

-0.81

acia

-0.80

dinand

-0.79

urai

-0.74

estones

-0.74

estyles

-0.73

assic

-0.73

natureconservancy

-0.72

HAEL

-0.71

POSITIVE LOGITS

abel

1.09

xual

0.89

edly

0.77

ais

0.76

ed

0.74

mental

0.70

 Warehouse

0.69

ãģĨ

0.67

ourgeois

0.65

witz

0.64

Activations Density 0.044%

names or terms related to labels or classifications

occurrences of the term "abel" and variations of it in different contexts

No Comments

No Known Activations