INDEX

Explanations

year numbers in documentation

oai_token-act-pair · gpt-3.5-turbo

numerical codes or identifiers, particularly related to statistics 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

iday

-0.83

ingham

-0.77

ary

-0.77

aries

-0.75

ishing

-0.74

igating

-0.73

ality

-0.71

apest

-0.69

ential

-0.69

igation

-0.69

POSITIVE LOGITS

teenth

0.93

0.84

ptive

0.79

ãģĨ

0.76

cffff

0.74

LECT

0.72

0.71

plate

0.70

UTH

0.68

 millenn

0.68

Activations Density 0.085%

year numbers in documentation

numerical codes or identifiers, particularly related to statistics or references

No Comments

No Known Activations