INDEX

Explanations

phrases related to numbers and lists

oai_token-act-pair · gpt-3.5-turbo

specific numeric identifiers or codes, particularly those associated with citations or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 tradem

-0.83

inates

-0.76

uations

-0.74

abwe

-0.69

kens

-0.67

pmwiki

-0.66

aution

-0.65

kes

-0.64

igible

-0.63

odies

-0.63

POSITIVE LOGITS

0.93

0.87

th

0.87

0.86

0.85

0.84

0.83

0.82

Activations Density 0.049%

phrases related to numbers and lists

specific numeric identifiers or codes, particularly those associated with citations or references

No Comments

No Known Activations