INDEX

Explanations

words related to physical hindrances or obstacles

oai_token-act-pair · gpt-3.5-turbo

terms related to ham and its various uses or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

URES

-0.72

URE

-0.66

 Statements

-0.66

 Corinth

-0.66

orious

-0.66

inia

-0.65

 Dame

-0.63

nces

-0.62

hips

-0.62

 Teach

-0.61

POSITIVE LOGITS

ilton

1.13

strings

1.13

stead

1.01

mers

1.00

ham

0.99

sters

0.98

pering

0.93

ming

0.92

pton

0.91

gob

0.89

Activations Density 0.007%

words related to physical hindrances or obstacles

terms related to ham and its various uses or references

No Comments

No Known Activations